{"meta": {"count": 288524, "db_response_time_ms": 651, "page": 1, "per_page": 25, "groups_count": null, "cost_usd": 0.001}, "results": [{"id": "https://openalex.org/W4404356490", "doi": "https://doi.org/10.1093/nsr/nwae403", "title": "A survey on multimodal large language models", "display_name": "A survey on multimodal large language models", "relevance_score": 3335.9167, "publication_year": 2024, "publication_date": "2024-11-12", "ids": {"openalex": "https://openalex.org/W4404356490", "doi": "https://doi.org/10.1093/nsr/nwae403", "pmid": "https://pubmed.ncbi.nlm.nih.gov/39679213"}, "language": "en", "primary_location": {"id": "doi:10.1093/nsr/nwae403", "is_oa": true, "landing_page_url": "https://doi.org/10.1093/nsr/nwae403", "pdf_url": null, "source": {"id": "https://openalex.org/S2734413303", "display_name": "National Science Review", "issn_l": "2053-714X", "issn": ["2053-714X", "2095-5138"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310311648", "host_organization_name": "Oxford University Press", "host_organization_lineage": ["https://openalex.org/P4310311648", "https://openalex.org/P4310311647"], "host_organization_lineage_names": ["Oxford University Press", "University of Oxford"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "National Science Review", "raw_type": "journal-article"}, "type": "review", "indexed_in": ["crossref", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://doi.org/10.1093/nsr/nwae403", "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073775343", "display_name": "Shukang Yin", "orcid": "https://orcid.org/0000-0002-5356-1800"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Shukang Yin", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014172220", "display_name": "Chaoyou Fu", "orcid": "https://orcid.org/0000-0002-0079-7668"}, "institutions": [{"id": "https://openalex.org/I308837", "display_name": "Suzhou University of Science and Technology", "ror": "https://ror.org/04en8wb91", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I308837"]}, {"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chaoyou Fu", "raw_affiliation_strings": ["School of Intelligence Science and Technology, Nanjing University , Suzhou 215163 ,", "State Key Laboratory for Novel Software Technology, Nanjing University , Nanjing 210023 ,", "State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China", "School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Intelligence Science and Technology, Nanjing University , Suzhou 215163 ,", "institution_ids": ["https://openalex.org/I308837", "https://openalex.org/I881766915"]}, {"raw_affiliation_string": "State Key Laboratory for Novel Software Technology, Nanjing University , Nanjing 210023 ,", "institution_ids": ["https://openalex.org/I881766915"]}, {"raw_affiliation_string": "State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China", "institution_ids": ["https://openalex.org/I881766915"]}, {"raw_affiliation_string": "School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China", "institution_ids": ["https://openalex.org/I308837", "https://openalex.org/I881766915"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5090369859", "display_name": "Sirui Zhao", "orcid": "https://orcid.org/0000-0001-8103-0321"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Sirui Zhao", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100655785", "display_name": "Ke Li", "orcid": "https://orcid.org/0000-0001-7199-9139"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ke Li", "raw_affiliation_strings": ["Tencent YouTu Lab , Shanghai 200233 ,", "Tencent YouTu Lab, Shanghai 200233, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent YouTu Lab , Shanghai 200233 ,", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent YouTu Lab, Shanghai 200233, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100388508", "display_name": "Xing Sun", "orcid": "https://orcid.org/0000-0002-7683-4517"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xing Sun", "raw_affiliation_strings": ["Tencent YouTu Lab , Shanghai 200233 ,", "Tencent YouTu Lab, Shanghai 200233, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent YouTu Lab , Shanghai 200233 ,", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent YouTu Lab, Shanghai 200233, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025292786", "display_name": "Tong Xu", "orcid": "https://orcid.org/0000-0003-4246-5386"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tong Xu", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048237545", "display_name": "Enhong Chen", "orcid": "https://orcid.org/0000-0002-4835-4102"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Enhong Chen", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China , Hefei 230026 ,", "institution_ids": ["https://openalex.org/I126520041"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5073775343"], "corresponding_institution_ids": ["https://openalex.org/I126520041"], "apc_list": {"value": 1904, "currency": "USD", "value_usd": 1904}, "apc_paid": {"value": 1904, "currency": "USD", "value_usd": 1904}, "fwci": 117.1698, "has_fulltext": false, "cited_by_count": 521, "citation_normalized_percentile": {"value": 0.99987806, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 90, "max": 100}, "biblio": {"volume": "11", "issue": "12", "first_page": "nwae403", "last_page": "nwae403"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9991000294685364, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9936000108718872, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.35622793436050415}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.32180124521255493}, {"id": "https://openalex.org/keywords/philosophy", "display_name": "Philosophy", "score": 0.17201367020606995}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.35622793436050415}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.32180124521255493}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.17201367020606995}], "mesh": [], "locations_count": 2, "locations": [{"id": "doi:10.1093/nsr/nwae403", "is_oa": true, "landing_page_url": "https://doi.org/10.1093/nsr/nwae403", "pdf_url": null, "source": {"id": "https://openalex.org/S2734413303", "display_name": "National Science Review", "issn_l": "2053-714X", "issn": ["2053-714X", "2095-5138"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310311648", "host_organization_name": "Oxford University Press", "host_organization_lineage": ["https://openalex.org/P4310311648", "https://openalex.org/P4310311647"], "host_organization_lineage_names": ["Oxford University Press", "University of Oxford"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "National Science Review", "raw_type": "journal-article"}, {"id": "pmid:39679213", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/39679213", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "National science review", "raw_type": null}], "best_oa_location": {"id": "doi:10.1093/nsr/nwae403", "is_oa": true, "landing_page_url": "https://doi.org/10.1093/nsr/nwae403", "pdf_url": null, "source": {"id": "https://openalex.org/S2734413303", "display_name": "National Science Review", "issn_l": "2053-714X", "issn": ["2053-714X", "2095-5138"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310311648", "host_organization_name": "Oxford University Press", "host_organization_lineage": ["https://openalex.org/P4310311648", "https://openalex.org/P4310311647"], "host_organization_lineage_names": ["Oxford University Press", "University of Oxford"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "National Science Review", "raw_type": "journal-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.47999998927116394, "display_name": "Quality Education"}], "awards": [{"id": "https://openalex.org/G1064288964", "display_name": null, "funder_award_id": "61727809", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G3604000827", "display_name": null, "funder_award_id": "62222213", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G3665707508", "display_name": null, "funder_award_id": "62406264", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G4442529403", "display_name": null, "funder_award_id": "U22B2059", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G4627299367", "display_name": null, "funder_award_id": "2023NSFSC1402", "funder_id": "https://openalex.org/F4320329861", "funder_display_name": "Natural Science Foundation of Sichuan Province"}, {"id": "https://openalex.org/G4862937960", "display_name": null, "funder_award_id": "U23A20319", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G7295420491", "display_name": null, "funder_award_id": "62072423", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}, {"id": "https://openalex.org/F4320329861", "display_name": "Natural Science Foundation of Sichuan Province", "ror": null}, {"id": "https://openalex.org/F4320335581", "display_name": "Young Scientists Fund", "ror": null}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 189, "referenced_works": ["https://openalex.org/W1583837637", "https://openalex.org/W1861492603", "https://openalex.org/W1905882502", "https://openalex.org/W1933349210", "https://openalex.org/W1956340063", "https://openalex.org/W2425121537", "https://openalex.org/W2489434015", "https://openalex.org/W2753032179", "https://openalex.org/W2753709519", "https://openalex.org/W2886641317", "https://openalex.org/W2904565150", "https://openalex.org/W2911445777", "https://openalex.org/W2914304175", "https://openalex.org/W2962735233", "https://openalex.org/W2963109634", "https://openalex.org/W2973379954", "https://openalex.org/W3012608737", "https://openalex.org/W3015591594", "https://openalex.org/W3096609285", "https://openalex.org/W3104279398", "https://openalex.org/W3176641147", "https://openalex.org/W3199693760", "https://openalex.org/W4281557623", "https://openalex.org/W4306820534", "https://openalex.org/W4307079201", "https://openalex.org/W4309804346", "https://openalex.org/W4322718191", "https://openalex.org/W4353113046", "https://openalex.org/W4361194507", "https://openalex.org/W4362515116", "https://openalex.org/W4362707064", "https://openalex.org/W4366400053", "https://openalex.org/W4367367040", "https://openalex.org/W4367628410", "https://openalex.org/W4368755685", "https://openalex.org/W4372266552", "https://openalex.org/W4372273323", "https://openalex.org/W4376122449", "https://openalex.org/W4376167553", "https://openalex.org/W4378501696", "https://openalex.org/W4378510493", "https://openalex.org/W4380137118", "https://openalex.org/W4381951819", "https://openalex.org/W4382142077", "https://openalex.org/W4382491206", "https://openalex.org/W4383604278", "https://openalex.org/W4384918448", "https://openalex.org/W4385570412", "https://openalex.org/W4385572634", "https://openalex.org/W4386065512", "https://openalex.org/W4386065691", "https://openalex.org/W4386071707", "https://openalex.org/W4386075985", "https://openalex.org/W4386076522", "https://openalex.org/W4386148496", "https://openalex.org/W4386185600", "https://openalex.org/W4386302587", "https://openalex.org/W4386555501", "https://openalex.org/W4386876368", "https://openalex.org/W4387294588", "https://openalex.org/W4387947626", "https://openalex.org/W4388444960", "https://openalex.org/W4388502440", "https://openalex.org/W4388585446", "https://openalex.org/W4388685765", "https://openalex.org/W4388685775", "https://openalex.org/W4389157280", "https://openalex.org/W4389519587", "https://openalex.org/W4389523832", "https://openalex.org/W4389983382", "https://openalex.org/W4390091503", "https://openalex.org/W4390136788", "https://openalex.org/W4390455781", "https://openalex.org/W4390874324", "https://openalex.org/W4390874575", "https://openalex.org/W4391376671", "https://openalex.org/W4391376827", "https://openalex.org/W4391987298", "https://openalex.org/W4392011716", "https://openalex.org/W4392627835", "https://openalex.org/W4393149524", "https://openalex.org/W4393220580", "https://openalex.org/W4395687490", "https://openalex.org/W4400033239", "https://openalex.org/W4401043272", "https://openalex.org/W4402670859", "https://openalex.org/W4402671548", "https://openalex.org/W4402716330", "https://openalex.org/W4402727405", "https://openalex.org/W4402727558", "https://openalex.org/W4402727635", "https://openalex.org/W4402727764", "https://openalex.org/W4402753581", "https://openalex.org/W4402753874", "https://openalex.org/W4402753951", "https://openalex.org/W4402754134", "https://openalex.org/W4403778769", "https://openalex.org/W4404575065", "https://openalex.org/W4404782964", "https://openalex.org/W4405595839", "https://openalex.org/W4405596328", "https://openalex.org/W6676497082", "https://openalex.org/W6767858076", "https://openalex.org/W6775041699", "https://openalex.org/W6778883912", "https://openalex.org/W6779823529", "https://openalex.org/W6782465632", "https://openalex.org/W6789909235", "https://openalex.org/W6791353385", "https://openalex.org/W6798805250", "https://openalex.org/W6800875267", "https://openalex.org/W6802669662", "https://openalex.org/W6804095316", "https://openalex.org/W6809646742", "https://openalex.org/W6810334672", "https://openalex.org/W6810738896", "https://openalex.org/W6811013733", "https://openalex.org/W6811467201", "https://openalex.org/W6839015040", "https://openalex.org/W6839041712", "https://openalex.org/W6843405348", "https://openalex.org/W6847076894", "https://openalex.org/W6849177959", "https://openalex.org/W6849677550", "https://openalex.org/W6850503672", "https://openalex.org/W6850625674", "https://openalex.org/W6850991314", "https://openalex.org/W6851513886", "https://openalex.org/W6851592950", "https://openalex.org/W6851623818", "https://openalex.org/W6851775633", "https://openalex.org/W6851948999", "https://openalex.org/W6851950068", "https://openalex.org/W6851960618", "https://openalex.org/W6852060543", "https://openalex.org/W6852087528", "https://openalex.org/W6852410717", "https://openalex.org/W6852418670", "https://openalex.org/W6852489829", "https://openalex.org/W6852667213", "https://openalex.org/W6852699137", "https://openalex.org/W6852773135", "https://openalex.org/W6852776751", "https://openalex.org/W6852784024", "https://openalex.org/W6852797390", "https://openalex.org/W6852818750", "https://openalex.org/W6852839128", "https://openalex.org/W6853116092", "https://openalex.org/W6853305943", "https://openalex.org/W6853469104", "https://openalex.org/W6853505628", "https://openalex.org/W6853875005", "https://openalex.org/W6854262950", "https://openalex.org/W6854263694", "https://openalex.org/W6854308264", "https://openalex.org/W6854347851", "https://openalex.org/W6854484269", "https://openalex.org/W6854695065", "https://openalex.org/W6854866820", "https://openalex.org/W6855350031", "https://openalex.org/W6855594702", "https://openalex.org/W6855759673", "https://openalex.org/W6856037140", "https://openalex.org/W6856560382", "https://openalex.org/W6856606850", "https://openalex.org/W6856794988", "https://openalex.org/W6856800273", "https://openalex.org/W6857241981", "https://openalex.org/W6857569170", "https://openalex.org/W6857614378", "https://openalex.org/W6857822741", "https://openalex.org/W6858247760", "https://openalex.org/W6858268588", "https://openalex.org/W6858380932", "https://openalex.org/W6858412945", "https://openalex.org/W6858603669", "https://openalex.org/W6858878845", "https://openalex.org/W6859010397", "https://openalex.org/W6859395458", "https://openalex.org/W6859462557", "https://openalex.org/W6859844524", "https://openalex.org/W6861475616", "https://openalex.org/W6861859004", "https://openalex.org/W6861874610", "https://openalex.org/W6862174374", "https://openalex.org/W6862276026", "https://openalex.org/W6862325135", "https://openalex.org/W6876048176", "https://openalex.org/W6917636526"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2899084033", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W4391913857", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052"], "abstract_inverted_index": {"Recently,": [0], "the": [1, 36, 86, 103, 111, 115, 173], "multimodal": [2, 29, 55, 154, 160, 163], "large": [3, 20], "language": [4, 21], "model": [5], "(MLLM)": [6], "represented": [7], "by": [8], "GPT-4V": [9], "has": [10], "been": [11], "a": [12, 25, 58, 91], "new": [13], "rising": [14], "research": [15, 89, 135, 183], "hotspot,": [16], "which": [17], "uses": [18], "powerful": [19], "models": [22], "(LLMs)": [23], "as": [24, 39, 128, 130], "brain": [26], "to": [27, 61, 74, 99, 143], "perform": [28], "tasks.": [30], "The": [31], "surprising": [32, 92], "emergent": [33], "capabilities": [34], "of": [35, 88, 106, 114, 165], "MLLM,": [37], "such": [38], "writing": [40], "stories": [41], "based": [42], "on": [43], "images": [44], "and": [45, 70, 101, 117, 126, 149, 156, 167, 179], "optical": [46], "character": [47], "recognition-free": [48], "math": [49], "reasoning,": [50], "are": [51], "rare": [52], "in": [53], "traditional": [54], "methods,": [56], "suggesting": [57], "potential": [59], "path": [60], "artificial": [62], "general": [63], "intelligence.": [64], "To": [65, 171], "this": [66, 95], "end,": [67], "both": [68], "academia": [69], "industry": [71], "have": [72], "endeavored": [73], "develop": [75], "MLLMs": [76, 139], "that": [77], "can": [78, 140], "compete": [79], "with": [80, 153], "or": [81], "even": [82], "outperform": [83], "GPT-4V,": [84], "pushing": [85], "limit": [87], "at": [90], "speed.": [93], "In": [94], "paper,": [96, 174], "we": [97, 109, 133, 175], "aim": [98], "trace": [100], "summarize": [102], "recent": [104], "progress": [105], "MLLMs.": [107], "First,": [108], "present": [110], "basic": [112], "formulation": [113], "MLLM": [116], "delineate": [118], "its": [119], "related": [120], "concepts,": [121], "including": [122, 159], "architecture,": [123], "training": [124], "strategy": [125], "data,": [127], "well": [129], "evaluation.": [131], "Then,": [132], "introduce": [134], "topics": [136], "about": [137], "how": [138], "be": [141], "extended": [142, 157], "support": [144], "more": [145], "granularity,": [146], "modalities,": [147], "languages": [148], "scenarios.": [150], "We": [151], "continue": [152], "hallucination": [155], "techniques,": [158], "in-context": [161], "learning,": [162], "chain": [164], "thought": [166], "LLM-aided": [168], "visual": [169], "reasoning.": [170], "conclude": [172], "discuss": [176], "existing": [177], "challenges": [178], "point": [180], "out": [181], "promising": [182], "directions.": [184]}, "counts_by_year": [{"year": 2026, "cited_by_count": 125}, {"year": 2025, "cited_by_count": 321}, {"year": 2024, "cited_by_count": 74}, {"year": 2023, "cited_by_count": 1}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4394862623", "doi": "https://doi.org/10.1109/wacvw60836.2024.00106", "title": "A Survey on Multimodal Large Language Models for Autonomous Driving", "display_name": "A Survey on Multimodal Large Language Models for Autonomous Driving", "relevance_score": 2213.7158, "publication_year": 2024, "publication_date": "2024-01-01", "ids": {"openalex": "https://openalex.org/W4394862623", "doi": "https://doi.org/10.1109/wacvw60836.2024.00106"}, "language": "en", "primary_location": {"id": "doi:10.1109/wacvw60836.2024.00106", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/wacvw60836.2024.00106", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5025560682", "display_name": "Can Cui", "orcid": "https://orcid.org/0000-0002-1783-623X"}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Can Cui", "raw_affiliation_strings": ["Purdue University,West Lafayette,IN,USA,47907"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University,West Lafayette,IN,USA,47907", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103050279", "display_name": "Yunsheng Ma", "orcid": "https://orcid.org/0000-0003-3933-2574"}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Yunsheng Ma", "raw_affiliation_strings": ["Purdue University,West Lafayette,IN,USA,47907"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University,West Lafayette,IN,USA,47907", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101247284", "display_name": "Xu Cao", "orcid": null}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xu Cao", "raw_affiliation_strings": ["University of Illinois Urbana-Champaign,Champaign,IL,USA,61801", "PediaMed AI, Shenzhen, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Illinois Urbana-Champaign,Champaign,IL,USA,61801", "institution_ids": ["https://openalex.org/I157725225"]}, {"raw_affiliation_string": "PediaMed AI, Shenzhen, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067298507", "display_name": "Wenqian Ye", "orcid": "https://orcid.org/0000-0002-6069-5153"}, "institutions": [{"id": "https://openalex.org/I51556381", "display_name": "University of Virginia", "ror": "https://ror.org/0153tk833", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I51556381"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Wenqian Ye", "raw_affiliation_strings": ["University of Virginia,Charlottesville,VA,USA,22903", "PediaMed AI, Shenzhen, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Virginia,Charlottesville,VA,USA,22903", "institution_ids": ["https://openalex.org/I51556381"]}, {"raw_affiliation_string": "PediaMed AI, Shenzhen, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107116548", "display_name": "Yang Zhou", "orcid": "https://orcid.org/0009-0006-3469-8058"}, "institutions": [{"id": "https://openalex.org/I57206974", "display_name": "New York University", "ror": "https://ror.org/0190ak572", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I57206974"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Yang Zhou", "raw_affiliation_strings": ["New York University,New York,NY,USA,11201"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "New York University,New York,NY,USA,11201", "institution_ids": ["https://openalex.org/I57206974"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062351534", "display_name": "Kaizhao Liang", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kaizhao Liang", "raw_affiliation_strings": ["SambaNova Systems, Inc,Palo Alto,CA,USA,94303"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SambaNova Systems, Inc,Palo Alto,CA,USA,94303", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5023258354", "display_name": "Jintai Chen", "orcid": "https://orcid.org/0000-0002-3199-2597"}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Jintai Chen", "raw_affiliation_strings": ["University of Illinois Urbana-Champaign,Champaign,IL,USA,61801"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Illinois Urbana-Champaign,Champaign,IL,USA,61801", "institution_ids": ["https://openalex.org/I157725225"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040085446", "display_name": "Juanwu Lu", "orcid": "https://orcid.org/0000-0003-0831-1244"}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Juanwu Lu", "raw_affiliation_strings": ["Purdue University,West Lafayette,IN,USA,47907"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University,West Lafayette,IN,USA,47907", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5104202411", "display_name": "Zichong Yang", "orcid": null}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Zichong Yang", "raw_affiliation_strings": ["Purdue University,West Lafayette,IN,USA,47907"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University,West Lafayette,IN,USA,47907", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101337811", "display_name": "Kuei-Da Liao", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kuei-Da Liao", "raw_affiliation_strings": ["Objective, Inc,San Francisco,CA,USA,94110"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Objective, Inc,San Francisco,CA,USA,94110", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089291480", "display_name": "Tianren Gao", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tianren Gao", "raw_affiliation_strings": ["SambaNova Systems, Inc,Palo Alto,CA,USA,94303"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SambaNova Systems, Inc,Palo Alto,CA,USA,94303", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024839365", "display_name": "Erlong Li", "orcid": null}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Erlong Li", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101941534", "display_name": "Tang Kun", "orcid": "https://orcid.org/0000-0002-8909-8467"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Kun Tang", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100635855", "display_name": "Zhipeng Cao", "orcid": "https://orcid.org/0009-0002-8308-4256"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhipeng Cao", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101777618", "display_name": "Tong Zhou", "orcid": "https://orcid.org/0000-0002-8645-5246"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tong Zhou", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100346428", "display_name": "Ao Liu", "orcid": "https://orcid.org/0009-0006-0953-4473"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ao Liu", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050579347", "display_name": "Xinrui Yan", "orcid": null}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xinrui Yan", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5059884876", "display_name": "Shuqi Mei", "orcid": "https://orcid.org/0000-0001-6512-7465"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shuqi Mei", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109654260", "display_name": "Jianguo Cao", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jianguo Cao", "raw_affiliation_strings": ["PediaMed AI,Shenzhen,China", "PediaMed AI, Shenzhen, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "PediaMed AI,Shenzhen,China", "institution_ids": []}, {"raw_affiliation_string": "PediaMed AI, Shenzhen, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038550389", "display_name": "Ziran Wang", "orcid": "https://orcid.org/0000-0003-2702-7150"}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ziran Wang", "raw_affiliation_strings": ["Purdue University,West Lafayette,IN,USA,47907"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University,West Lafayette,IN,USA,47907", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101337812", "display_name": "Chao Zheng", "orcid": null}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chao Zheng", "raw_affiliation_strings": ["Tencent T Lab,Beijing,China", "Tencent T Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent T Lab,Beijing,China", "institution_ids": ["https://openalex.org/I2250653659"]}, {"raw_affiliation_string": "Tencent T Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 21, "corresponding_author_ids": ["https://openalex.org/A5025560682"], "corresponding_institution_ids": ["https://openalex.org/I219193219"], "apc_list": null, "apc_paid": null, "fwci": 60.6856, "has_fulltext": false, "cited_by_count": 268, "citation_normalized_percentile": {"value": 0.99951225, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "958", "last_page": "979"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9991999864578247, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9991999864578247, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9986000061035156, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9908999800682068, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.7094346880912781}, {"id": "https://openalex.org/keywords/human\u2013computer-interaction", "display_name": "Human\u2013computer interaction", "score": 0.4377460479736328}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.7094346880912781}, {"id": "https://openalex.org/C107457646", "wikidata": "https://www.wikidata.org/wiki/Q207434", "display_name": "Human\u2013computer interaction", "level": 1, "score": 0.4377460479736328}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/wacvw60836.2024.00106", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/wacvw60836.2024.00106", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 223, "referenced_works": ["https://openalex.org/W1503933356", "https://openalex.org/W1525482321", "https://openalex.org/W1608789752", "https://openalex.org/W1614298861", "https://openalex.org/W1636244751", "https://openalex.org/W1811254738", "https://openalex.org/W1895577753", "https://openalex.org/W1905882502", "https://openalex.org/W1924770834", "https://openalex.org/W1933349210", "https://openalex.org/W1985261475", "https://openalex.org/W2000840273", "https://openalex.org/W2047030012", "https://openalex.org/W2050047175", "https://openalex.org/W2064675550", "https://openalex.org/W2070183171", "https://openalex.org/W2076379374", "https://openalex.org/W2094430142", "https://openalex.org/W2121227244", "https://openalex.org/W2130942839", "https://openalex.org/W2131774270", "https://openalex.org/W2139137304", "https://openalex.org/W2150066425", "https://openalex.org/W2154844948", "https://openalex.org/W2167224731", "https://openalex.org/W2206222117", "https://openalex.org/W2339077268", "https://openalex.org/W2560609797", "https://openalex.org/W2609532991", "https://openalex.org/W2619697695", "https://openalex.org/W2780740184", "https://openalex.org/W2798786289", "https://openalex.org/W2885138528", "https://openalex.org/W2896457183", "https://openalex.org/W2904393593", "https://openalex.org/W2904904015", "https://openalex.org/W2934625602", "https://openalex.org/W2951725892", "https://openalex.org/W2953303875", "https://openalex.org/W2955189650", "https://openalex.org/W2963367210", "https://openalex.org/W2964915587", "https://openalex.org/W2966715458", "https://openalex.org/W2968124245", "https://openalex.org/W2968176166", "https://openalex.org/W2968296999", "https://openalex.org/W2968983352", "https://openalex.org/W2970603850", "https://openalex.org/W2981207549", "https://openalex.org/W2996542533", "https://openalex.org/W2996811802", "https://openalex.org/W3000280594", "https://openalex.org/W3003205975", "https://openalex.org/W3003954087", "https://openalex.org/W3034550906", "https://openalex.org/W3035172746", "https://openalex.org/W3035265375", "https://openalex.org/W3035574168", "https://openalex.org/W3037309139", "https://openalex.org/W3046086546", "https://openalex.org/W3100923070", "https://openalex.org/W3104529101", "https://openalex.org/W3117243625", "https://openalex.org/W3118497696", "https://openalex.org/W3127561923", "https://openalex.org/W3133150807", "https://openalex.org/W3133465684", "https://openalex.org/W3147794100", "https://openalex.org/W3156470785", "https://openalex.org/W3166396011", "https://openalex.org/W3173844397", "https://openalex.org/W3176484337", "https://openalex.org/W3181942264", "https://openalex.org/W3182832188", "https://openalex.org/W3191652410", "https://openalex.org/W3193402170", "https://openalex.org/W3203511201", "https://openalex.org/W3205423339", "https://openalex.org/W4200081143", "https://openalex.org/W4206415992", "https://openalex.org/W4221143046", "https://openalex.org/W4221152848", "https://openalex.org/W4224308101", "https://openalex.org/W4224912544", "https://openalex.org/W4225323055", "https://openalex.org/W4226244192", "https://openalex.org/W4226278401", "https://openalex.org/W4226352076", "https://openalex.org/W4234151133", "https://openalex.org/W4251852706", "https://openalex.org/W4281557260", "https://openalex.org/W4283788970", "https://openalex.org/W4285428875", "https://openalex.org/W4285483774", "https://openalex.org/W4285603535", "https://openalex.org/W4286987939", "https://openalex.org/W4286989192", "https://openalex.org/W4287113019", "https://openalex.org/W4288089799", "https://openalex.org/W4292779060", "https://openalex.org/W4307079201", "https://openalex.org/W4312205996", "https://openalex.org/W4312420092", "https://openalex.org/W4312550876", "https://openalex.org/W4312933868", "https://openalex.org/W4313026212", "https://openalex.org/W4313483544", "https://openalex.org/W4318718936", "https://openalex.org/W4319300501", "https://openalex.org/W4321275178", "https://openalex.org/W4322718191", "https://openalex.org/W4323572061", "https://openalex.org/W4323717348", "https://openalex.org/W4353113046", "https://openalex.org/W4361866031", "https://openalex.org/W4366330503", "https://openalex.org/W4366400053", "https://openalex.org/W4366566341", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4368755685", "https://openalex.org/W4372266769", "https://openalex.org/W4372273323", "https://openalex.org/W4377866264", "https://openalex.org/W4378505261", "https://openalex.org/W4381797997", "https://openalex.org/W4382317933", "https://openalex.org/W4383097638", "https://openalex.org/W4383108457", "https://openalex.org/W4383605194", "https://openalex.org/W4384264726", "https://openalex.org/W4384918448", "https://openalex.org/W4385245566", "https://openalex.org/W4385567149", "https://openalex.org/W4385805185", "https://openalex.org/W4385953069", "https://openalex.org/W4386065691", "https://openalex.org/W4386066469", "https://openalex.org/W4386075985", "https://openalex.org/W4386076252", "https://openalex.org/W4386621530", "https://openalex.org/W4386651426", "https://openalex.org/W4386651449", "https://openalex.org/W4386918877", "https://openalex.org/W4386977420", "https://openalex.org/W4387074810", "https://openalex.org/W4387221829", "https://openalex.org/W4387294122", "https://openalex.org/W4387323024", "https://openalex.org/W4387389637", "https://openalex.org/W4387390364", "https://openalex.org/W4387560742", "https://openalex.org/W4387687043", "https://openalex.org/W4387724762", "https://openalex.org/W4387741824", "https://openalex.org/W4388901335", "https://openalex.org/W4389519587", "https://openalex.org/W4389520282", "https://openalex.org/W4390437464", "https://openalex.org/W4390871966", "https://openalex.org/W4390872108", "https://openalex.org/W4390873054", "https://openalex.org/W4390874283", "https://openalex.org/W4390874575", "https://openalex.org/W4391770362", "https://openalex.org/W4393148430", "https://openalex.org/W4394595621", "https://openalex.org/W4394828156", "https://openalex.org/W4394841941", "https://openalex.org/W4394843896", "https://openalex.org/W4394862582", "https://openalex.org/W4394862611", "https://openalex.org/W4394862732", "https://openalex.org/W4394862768", "https://openalex.org/W4394862786", "https://openalex.org/W4399177289", "https://openalex.org/W4401386967", "https://openalex.org/W4401414574", "https://openalex.org/W4401416408", "https://openalex.org/W4403586856", "https://openalex.org/W4404356490", "https://openalex.org/W6631553122", "https://openalex.org/W6636510571", "https://openalex.org/W6638742206", "https://openalex.org/W6640212811", "https://openalex.org/W6679436768", "https://openalex.org/W6684338915", "https://openalex.org/W6755207826", "https://openalex.org/W6766904570", "https://openalex.org/W6767279747", "https://openalex.org/W6769627184", "https://openalex.org/W6778883912", "https://openalex.org/W6780294235", "https://openalex.org/W6790978476", "https://openalex.org/W6791353385", "https://openalex.org/W6797716411", "https://openalex.org/W6800139874", "https://openalex.org/W6801880476", "https://openalex.org/W6809646742", "https://openalex.org/W6810334672", "https://openalex.org/W6810738896", "https://openalex.org/W6838865847", "https://openalex.org/W6839459284", "https://openalex.org/W6840200333", "https://openalex.org/W6843491192", "https://openalex.org/W6848909144", "https://openalex.org/W6849177959", "https://openalex.org/W6850071225", "https://openalex.org/W6851513886", "https://openalex.org/W6851592950", "https://openalex.org/W6852410717", "https://openalex.org/W6852803816", "https://openalex.org/W6852823658", "https://openalex.org/W6852989508", "https://openalex.org/W6853562202", "https://openalex.org/W6854454755", "https://openalex.org/W6856128069", "https://openalex.org/W6856594407", "https://openalex.org/W6857112689", "https://openalex.org/W6857455582", "https://openalex.org/W6857506908", "https://openalex.org/W6858299849", "https://openalex.org/W6963811058"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W2382290278", "https://openalex.org/W4391913857", "https://openalex.org/W2350741829", "https://openalex.org/W2530322880"], "abstract_inverted_index": {"With": [0], "the": [1, 21, 26, 90, 98, 105, 131, 150, 164], "emergence": [2], "of": [3, 59, 63, 92, 107, 153, 166], "Large": [4, 94, 139], "Language": [5, 95, 140], "Models": [6, 11, 96, 143], "(LLMs)": [7], "and": [8, 31, 47, 67, 104, 119, 126, 141, 190], "Vision": [9, 142], "Foundation": [10], "(VFMs),": [12], "multimodal": [13, 99], "AI": [14], "systems": [15, 121, 181], "benefiting": [16], "from": [17], "large": [18], "models": [19, 100], "have": [20, 40], "potential": [22], "to": [23, 70, 184], "equally": [24], "perceive": [25], "real": [27], "world,": [28], "make": [29], "decisions,": [30], "control": [32], "tools": [33, 115], "as": [34], "humans.": [35], "In": [36, 76], "recent": [37], "months,": [38], "LLMs": [39, 157], "shown": [41], "widespread": [42], "attention": [43], "in": [44, 72, 84, 133, 158, 178], "autonomous": [45, 108, 159, 179], "driving": [46, 74, 180], "map": [48, 120], "systems.": [49, 75], "Despite": [50], "its": [51, 154], "immense": [52], "potential,": [53], "there": [54], "is": [55, 149], "still": [56], "a": [57, 60, 81], "lack": [58], "comprehensive": [61], "understanding": [62], "key": [64], "challenges,": [65], "opportunities,": [66], "future": [68], "endeavors": [69], "apply": [71], "LLM": [73], "this": [77, 85, 167], "paper,": [78], "we": [79, 111, 129, 169], "present": [80], "systematic": [82], "investigation": [83], "field.": [86], "We": [87], "first": [88, 151], "introduce": [89], "background": [91], "Multimodal": [93], "(MLLMs),": [97], "development": [101, 165], "using": [102, 176], "LLMs,": [103], "history": [106], "driving.": [109, 160], "Then,": [110], "overview": [112], "existing": [113, 124], "MLLM": [114], "for": [116, 144], "driving,": [117], "transportation,": [118], "together": [122], "with": [123], "datasets": [125], "benchmarks.": [127], "Moreover,": [128], "summarized": [130], "works": [132], "The": [134], "1st": [135], "WACV": [136], "Workshop": [137], "on": [138], "Autonomous": [145], "Driving": [146], "(LLVM-AD),": [147], "which": [148], "workshop": [152], "kind": [155], "regarding": [156, 175], "To": [161], "further": [162], "promote": [163], "field,": [168], "also": [170], "discuss": [171], "several": [172], "important": [173], "problems": [174], "MLLMs": [177], "that": [182], "need": [183], "be": [185], "solved": [186], "by": [187], "both": [188], "academia": [189], "industry.": [191]}, "counts_by_year": [{"year": 2026, "cited_by_count": 26}, {"year": 2025, "cited_by_count": 144}, {"year": 2024, "cited_by_count": 98}], "updated_date": "2026-05-19T08:33:51.333923", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4391094120", "doi": "https://doi.org/10.1109/bigdata59044.2023.10386743", "title": "Multimodal Large Language Models: A Survey", "display_name": "Multimodal Large Language Models: A Survey", "relevance_score": 2027.4237, "publication_year": 2023, "publication_date": "2023-12-15", "ids": {"openalex": "https://openalex.org/W4391094120", "doi": "https://doi.org/10.1109/bigdata59044.2023.10386743"}, "language": "en", "primary_location": {"id": "doi:10.1109/bigdata59044.2023.10386743", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/bigdata59044.2023.10386743", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2023 IEEE International Conference on Big Data (BigData)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5024848410", "display_name": "Jiayang Wu", "orcid": "https://orcid.org/0009-0001-1847-594X"}, "institutions": [{"id": "https://openalex.org/I159948400", "display_name": "Jinan University", "ror": "https://ror.org/02xe5ns62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I159948400"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jiayang Wu", "raw_affiliation_strings": ["Jinan University,Guangzhou,China,510632"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Jinan University,Guangzhou,China,510632", "institution_ids": ["https://openalex.org/I159948400"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000962921", "display_name": "Wensheng Gan", "orcid": "https://orcid.org/0000-0002-5781-8116"}, "institutions": [{"id": "https://openalex.org/I159948400", "display_name": "Jinan University", "ror": "https://ror.org/02xe5ns62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I159948400"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wensheng Gan", "raw_affiliation_strings": ["Jinan University,Guangzhou,China,510632", "Pazhou Lab, Guangzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Jinan University,Guangzhou,China,510632", "institution_ids": ["https://openalex.org/I159948400"]}, {"raw_affiliation_string": "Pazhou Lab, Guangzhou, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100704826", "display_name": "Zefeng Chen", "orcid": "https://orcid.org/0000-0002-5951-0051"}, "institutions": [{"id": "https://openalex.org/I159948400", "display_name": "Jinan University", "ror": "https://ror.org/02xe5ns62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I159948400"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zefeng Chen", "raw_affiliation_strings": ["Jinan University,Guangzhou,China,510632"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Jinan University,Guangzhou,China,510632", "institution_ids": ["https://openalex.org/I159948400"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005570140", "display_name": "Shicheng Wan", "orcid": "https://orcid.org/0000-0002-1051-9426"}, "institutions": [{"id": "https://openalex.org/I90610280", "display_name": "South China University of Technology", "ror": "https://ror.org/0530pts50", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I90610280"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shicheng Wan", "raw_affiliation_strings": ["South China University of Technology,Guangzhou,China,510641"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "South China University of Technology,Guangzhou,China,510641", "institution_ids": ["https://openalex.org/I90610280"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5036357902", "display_name": "Philip S. Yu", "orcid": "https://orcid.org/0000-0002-3491-5968"}, "institutions": [{"id": "https://openalex.org/I39422238", "display_name": "University of Illinois Chicago", "ror": "https://ror.org/02mpq6x41", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I39422238"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Philip S. Yu", "raw_affiliation_strings": ["The University of Illinois Chicago,Chicago,USA", "The University of Illinois Chicago, Chicago, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The University of Illinois Chicago,Chicago,USA", "institution_ids": ["https://openalex.org/I39422238"]}, {"raw_affiliation_string": "The University of Illinois Chicago, Chicago, USA", "institution_ids": ["https://openalex.org/I39422238"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 5, "corresponding_author_ids": ["https://openalex.org/A5024848410"], "corresponding_institution_ids": ["https://openalex.org/I159948400"], "apc_list": null, "apc_paid": null, "fwci": 33.6387, "has_fulltext": false, "cited_by_count": 202, "citation_normalized_percentile": {"value": 0.99821171, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 96, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "2247", "last_page": "2256"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.975600004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.975600004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9693999886512756, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.666495680809021}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.35925042629241943}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.32297709584236145}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.666495680809021}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.35925042629241943}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.32297709584236145}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/bigdata59044.2023.10386743", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/bigdata59044.2023.10386743", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2023 IEEE International Conference on Big Data (BigData)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.5600000023841858, "display_name": "Quality Education"}], "awards": [], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 103, "referenced_works": ["https://openalex.org/W1494198834", "https://openalex.org/W1877570817", "https://openalex.org/W1899558658", "https://openalex.org/W1989689139", "https://openalex.org/W2098973983", "https://openalex.org/W2118407121", "https://openalex.org/W2125113755", "https://openalex.org/W2125336414", "https://openalex.org/W2125384475", "https://openalex.org/W2144942180", "https://openalex.org/W2145012698", "https://openalex.org/W2277195237", "https://openalex.org/W2302086703", "https://openalex.org/W2425121537", "https://openalex.org/W2565989828", "https://openalex.org/W2592535880", "https://openalex.org/W2599124244", "https://openalex.org/W2952122856", "https://openalex.org/W2952132648", "https://openalex.org/W2965373594", "https://openalex.org/W2991044292", "https://openalex.org/W3081492798", "https://openalex.org/W3101140821", "https://openalex.org/W3101631197", "https://openalex.org/W3108425892", "https://openalex.org/W3110019360", "https://openalex.org/W3112103703", "https://openalex.org/W3154411171", "https://openalex.org/W3184735396", "https://openalex.org/W3194672963", "https://openalex.org/W3197736584", "https://openalex.org/W3199693760", "https://openalex.org/W3203711169", "https://openalex.org/W3204588463", "https://openalex.org/W3208314443", "https://openalex.org/W3209710747", "https://openalex.org/W4224035735", "https://openalex.org/W4253090855", "https://openalex.org/W4281485151", "https://openalex.org/W4287113019", "https://openalex.org/W4288089799", "https://openalex.org/W4296406182", "https://openalex.org/W4307640249", "https://openalex.org/W4312107707", "https://openalex.org/W4312784228", "https://openalex.org/W4318351475", "https://openalex.org/W4321649710", "https://openalex.org/W4322718246", "https://openalex.org/W4323572061", "https://openalex.org/W4323717348", "https://openalex.org/W4327545654", "https://openalex.org/W4353113046", "https://openalex.org/W4361229539", "https://openalex.org/W4365601405", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4379929801", "https://openalex.org/W4382132560", "https://openalex.org/W4385245566", "https://openalex.org/W4385567126", "https://openalex.org/W4385574156", "https://openalex.org/W4387969587", "https://openalex.org/W4388685466", "https://openalex.org/W4391093958", "https://openalex.org/W4391097696", "https://openalex.org/W6602113894", "https://openalex.org/W6636510571", "https://openalex.org/W6686207219", "https://openalex.org/W6691399679", "https://openalex.org/W6739901393", "https://openalex.org/W6741217325", "https://openalex.org/W6755207826", "https://openalex.org/W6766673545", "https://openalex.org/W6769627184", "https://openalex.org/W6771467084", "https://openalex.org/W6784333009", "https://openalex.org/W6791353385", "https://openalex.org/W6796761347", "https://openalex.org/W6797716411", "https://openalex.org/W6798805250", "https://openalex.org/W6800139874", "https://openalex.org/W6800813123", "https://openalex.org/W6809885388", "https://openalex.org/W6810049204", "https://openalex.org/W6838617955", "https://openalex.org/W6838639034", "https://openalex.org/W6842585177", "https://openalex.org/W6847903763", "https://openalex.org/W6849105126", "https://openalex.org/W6849177959", "https://openalex.org/W6849307739", "https://openalex.org/W6850015000", "https://openalex.org/W6850071225", "https://openalex.org/W6850140740", "https://openalex.org/W6850202480", "https://openalex.org/W6850503672", "https://openalex.org/W6851592950", "https://openalex.org/W6851596329", "https://openalex.org/W6851948999", "https://openalex.org/W6851950068", "https://openalex.org/W6852989508", "https://openalex.org/W6857785731", "https://openalex.org/W6863163599"], "related_works": ["https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W2382290278", "https://openalex.org/W2350741829", "https://openalex.org/W2530322880", "https://openalex.org/W1596801655", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"The": [0], "exploration": [1], "of": [2, 53, 63, 70, 78, 85, 100, 108, 130, 153], "multimodal": [3, 64, 71, 79, 101, 131, 154], "language": [4, 23], "models": [5, 24, 40, 132, 155], "integrates": [6], "multiple": [7], "data": [8, 37], "types,": [9], "such": [10], "as": [11], "images,": [12], "text,": [13], "language,": [14], "audio,": [15], "and": [16, 34, 65, 112, 123, 133, 156], "other": [17, 36], "heterogeneity.": [18], "While": [19], "the": [20, 61, 67, 83, 97, 109, 128, 135], "latest": [21, 110], "large": [22], "excel": [25], "in": [26, 159], "text-based": [27], "tasks,": [28], "they": [29], "often": [30], "struggle": [31], "to": [32, 148], "understand": [33], "process": [35], "types.": [38], "Multimodal": [39], "address": [41], "this": [42, 145], "limitation": [43], "by": [44, 59], "combining": [45], "various": [46, 160], "modalities,": [47], "enabling": [48], "a": [49, 76, 106, 150], "more": [50], "comprehensive": [51], "understanding": [52, 152], "diverse": [54], "data.": [55], "This": [56], "paper": [57, 146], "begins": [58], "defining": [60], "concept": [62], "examining": [66], "historical": [68], "development": [69], "algorithms.": [72], "Furthermore,": [73], "we": [74, 104, 126], "introduce": [75], "range": [77], "products,": [80], "focusing": [81], "on": [82], "efforts": [84], "major": [86], "technology": [87], "companies.": [88], "A": [89], "practical": [90], "guide": [91], "is": [92], "provided,": [93], "offering": [94], "insights": [95], "into": [96], "technical": [98], "aspects": [99], "models.": [102], "Moreover,": [103], "present": [105], "compilation": [107], "algorithms": [111], "commonly": [113], "used": [114], "datasets,": [115], "providing": [116], "researchers": [117], "with": [118, 138], "valuable": [119], "resources": [120], "for": [121], "experimentation": [122], "evaluation.": [124], "Lastly,": [125], "explore": [127], "applications": [129], "discuss": [134], "challenges": [136], "associated": [137], "their": [139, 157], "development.": [140], "By": [141], "addressing": [142], "these": [143], "aspects,": [144], "aims": [147], "facilitate": [149], "deeper": [151], "potentiality": [158], "domains.": [161]}, "counts_by_year": [{"year": 2026, "cited_by_count": 35}, {"year": 2025, "cited_by_count": 121}, {"year": 2024, "cited_by_count": 43}, {"year": 2023, "cited_by_count": 3}], "updated_date": "2026-05-19T08:33:51.333923", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402155831", "doi": "https://doi.org/10.2196/59505", "title": "Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook", "display_name": "Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook", "relevance_score": 1669.4204, "publication_year": 2024, "publication_date": "2024-08-20", "ids": {"openalex": "https://openalex.org/W4402155831", "doi": "https://doi.org/10.2196/59505", "pmid": "https://pubmed.ncbi.nlm.nih.gov/39321458"}, "language": "en", "primary_location": {"id": "doi:10.2196/59505", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/59505", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://doi.org/10.2196/59505", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5016543807", "display_name": "Rawan AlSaad", "orcid": "https://orcid.org/0000-0002-3235-0860"}, "institutions": [{"id": "https://openalex.org/I4210152471", "display_name": "Weill Cornell Medical College in Qatar", "ror": "https://ror.org/05v5hg569", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210152471"]}], "countries": ["QA"], "is_corresponding": true, "raw_author_name": "Rawan AlSaad", "raw_affiliation_strings": ["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0002-3235-0860", "affiliations": [{"raw_affiliation_string": "Weill Cornell Medicine-Qatar, Education City, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210152471"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103070560", "display_name": "Alaa Abd\u2010Alrazaq", "orcid": "https://orcid.org/0000-0001-7695-4626"}, "institutions": [{"id": "https://openalex.org/I4210152471", "display_name": "Weill Cornell Medical College in Qatar", "ror": "https://ror.org/05v5hg569", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210152471"]}], "countries": ["QA"], "is_corresponding": false, "raw_author_name": "Alaa Abd-alrazaq", "raw_affiliation_strings": ["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0001-7695-4626", "affiliations": [{"raw_affiliation_string": "Weill Cornell Medicine-Qatar, Education City, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210152471"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052314657", "display_name": "Sabri Boughorbel", "orcid": "https://orcid.org/0000-0003-2734-3356"}, "institutions": [{"id": "https://openalex.org/I4210144839", "display_name": "Hamad bin Khalifa University", "ror": "https://ror.org/03eyq4y97", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210144839"]}], "countries": ["QA"], "is_corresponding": false, "raw_author_name": "Sabri Boughorbel", "raw_affiliation_strings": ["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0003-2734-3356", "affiliations": [{"raw_affiliation_string": "Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210144839"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5001592898", "display_name": "Arfan Ahmed", "orcid": "https://orcid.org/0000-0002-4025-5767"}, "institutions": [{"id": "https://openalex.org/I4210152471", "display_name": "Weill Cornell Medical College in Qatar", "ror": "https://ror.org/05v5hg569", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210152471"]}], "countries": ["QA"], "is_corresponding": false, "raw_author_name": "Arfan Ahmed", "raw_affiliation_strings": ["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0002-4025-5767", "affiliations": [{"raw_affiliation_string": "Weill Cornell Medicine-Qatar, Education City, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210152471"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5048929154", "display_name": "Max-Antoine Renault", "orcid": "https://orcid.org/0000-0002-6558-0136"}, "institutions": [{"id": "https://openalex.org/I4210152471", "display_name": "Weill Cornell Medical College in Qatar", "ror": "https://ror.org/05v5hg569", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210152471"]}], "countries": ["QA"], "is_corresponding": false, "raw_author_name": "Max-Antoine Renault", "raw_affiliation_strings": ["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0002-6558-0136", "affiliations": [{"raw_affiliation_string": "Weill Cornell Medicine-Qatar, Education City, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210152471"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079507190", "display_name": "Rafat Damseh", "orcid": "https://orcid.org/0000-0001-6797-0448"}, "institutions": [{"id": "https://openalex.org/I201726411", "display_name": "United Arab Emirates University", "ror": "https://ror.org/01km6p862", "country_code": "AE", "type": "education", "lineage": ["https://openalex.org/I201726411"]}], "countries": ["AE"], "is_corresponding": false, "raw_author_name": "Rafat Damseh", "raw_affiliation_strings": ["Department of Computer Science and Software Engineering, United Arab Emirates University, Al Ain, United Arab Emirates"], "raw_orcid": "https://orcid.org/0000-0001-6797-0448", "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Software Engineering, United Arab Emirates University, Al Ain, United Arab Emirates", "institution_ids": ["https://openalex.org/I201726411"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5045843215", "display_name": "Javaid I. Sheikh", "orcid": "https://orcid.org/0000-0002-5762-4186"}, "institutions": [{"id": "https://openalex.org/I4210152471", "display_name": "Weill Cornell Medical College in Qatar", "ror": "https://ror.org/05v5hg569", "country_code": "QA", "type": "education", "lineage": ["https://openalex.org/I4210152471"]}], "countries": ["QA"], "is_corresponding": false, "raw_author_name": "Javaid Sheikh", "raw_affiliation_strings": ["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"], "raw_orcid": "https://orcid.org/0000-0002-5762-4186", "affiliations": [{"raw_affiliation_string": "Weill Cornell Medicine-Qatar, Education City, Doha, Qatar", "institution_ids": ["https://openalex.org/I4210152471"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5016543807"], "corresponding_institution_ids": ["https://openalex.org/I4210152471"], "apc_list": {"value": 2950, "currency": "USD", "value_usd": 2950}, "apc_paid": {"value": 2950, "currency": "USD", "value_usd": 2950}, "fwci": 72.0534, "has_fulltext": false, "cited_by_count": 228, "citation_normalized_percentile": {"value": 0.9994902, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "26", "issue": null, "first_page": "e59505", "last_page": "e59505"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9962999820709229, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9962999820709229, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9911999702453613, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.9329000115394592, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/preprint", "display_name": "Preprint", "score": 0.8601997494697571}, {"id": "https://openalex.org/keywords/health-care", "display_name": "Health care", "score": 0.5264766216278076}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.46330979466438293}, {"id": "https://openalex.org/keywords/data-science", "display_name": "Data science", "score": 0.34741538763046265}, {"id": "https://openalex.org/keywords/world-wide-web", "display_name": "World Wide Web", "score": 0.29817676544189453}, {"id": "https://openalex.org/keywords/political-science", "display_name": "Political science", "score": 0.15827849507331848}], "concepts": [{"id": "https://openalex.org/C43169469", "wikidata": "https://www.wikidata.org/wiki/Q580922", "display_name": "Preprint", "level": 2, "score": 0.8601997494697571}, {"id": "https://openalex.org/C160735492", "wikidata": "https://www.wikidata.org/wiki/Q31207", "display_name": "Health care", "level": 2, "score": 0.5264766216278076}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.46330979466438293}, {"id": "https://openalex.org/C2522767166", "wikidata": "https://www.wikidata.org/wiki/Q2374463", "display_name": "Data science", "level": 1, "score": 0.34741538763046265}, {"id": "https://openalex.org/C136764020", "wikidata": "https://www.wikidata.org/wiki/Q466", "display_name": "World Wide Web", "level": 1, "score": 0.29817676544189453}, {"id": "https://openalex.org/C17744445", "wikidata": "https://www.wikidata.org/wiki/Q36442", "display_name": "Political science", "level": 0, "score": 0.15827849507331848}, {"id": "https://openalex.org/C199539241", "wikidata": "https://www.wikidata.org/wiki/Q7748", "display_name": "Law", "level": 1, "score": 0.0}], "mesh": [{"descriptor_ui": "D003695", "descriptor_name": "Delivery of Health Care", "qualifier_ui": "Q000639", "qualifier_name": "trends", "is_major_topic": true}, {"descriptor_ui": "D003695", "descriptor_name": "Delivery of Health Care", "qualifier_ui": "Q000639", "qualifier_name": "trends", "is_major_topic": true}, {"descriptor_ui": "D003695", "descriptor_name": "Delivery of Health Care", "qualifier_ui": "Q000639", "qualifier_name": "trends", "is_major_topic": true}, {"descriptor_ui": "D003695", "descriptor_name": "Delivery of Health Care", "qualifier_ui": "Q000639", "qualifier_name": "trends", "is_major_topic": true}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D009323", "descriptor_name": "Natural Language Processing", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D009323", "descriptor_name": "Natural Language Processing", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D009323", "descriptor_name": "Natural Language Processing", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D009323", "descriptor_name": "Natural Language Processing", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D057286", "descriptor_name": "Electronic Health Records", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D057286", "descriptor_name": "Electronic Health Records", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D057286", "descriptor_name": "Electronic Health Records", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D057286", "descriptor_name": "Electronic Health Records", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}], "locations_count": 4, "locations": [{"id": "doi:10.2196/59505", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/59505", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, {"id": "pmid:39321458", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/39321458", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of medical Internet research", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:11464944", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/11464944", "pdf_url": null, "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "J Med Internet Res", "raw_type": "Text"}, {"id": "pmh:oai:doaj.org/article:9beb43fdc56549adb37979a638349b19", "is_oa": false, "landing_page_url": "https://doaj.org/article/9beb43fdc56549adb37979a638349b19", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401280", "display_name": "DOAJ (DOAJ: Directory of Open Access Journals)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Journal of Medical Internet Research, Vol 26, p e59505 (2024)", "raw_type": "article"}], "best_oa_location": {"id": "doi:10.2196/59505", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/59505", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 172, "referenced_works": ["https://openalex.org/W1821462560", "https://openalex.org/W1922655562", "https://openalex.org/W2064675550", "https://openalex.org/W2168610667", "https://openalex.org/W2194775991", "https://openalex.org/W2345512687", "https://openalex.org/W2606722458", "https://openalex.org/W2766839578", "https://openalex.org/W2889664156", "https://openalex.org/W2895917461", "https://openalex.org/W2905657479", "https://openalex.org/W2911489562", "https://openalex.org/W2952935243", "https://openalex.org/W2962835968", "https://openalex.org/W2963400886", "https://openalex.org/W2972119347", "https://openalex.org/W2983587580", "https://openalex.org/W2996550193", "https://openalex.org/W3009260245", "https://openalex.org/W3017637887", "https://openalex.org/W3018610833", "https://openalex.org/W3038035611", "https://openalex.org/W3046375318", "https://openalex.org/W3094502228", "https://openalex.org/W3107627743", "https://openalex.org/W3122765966", "https://openalex.org/W3127238141", "https://openalex.org/W3128912454", "https://openalex.org/W3129155125", "https://openalex.org/W3168867926", "https://openalex.org/W3174057701", "https://openalex.org/W3177049011", "https://openalex.org/W3177500196", "https://openalex.org/W3193158708", "https://openalex.org/W3195980265", "https://openalex.org/W4205773061", "https://openalex.org/W4220867361", "https://openalex.org/W4221022534", "https://openalex.org/W4225917625", "https://openalex.org/W4225966403", "https://openalex.org/W4226196842", "https://openalex.org/W4281643269", "https://openalex.org/W4285987711", "https://openalex.org/W4288421316", "https://openalex.org/W4292438865", "https://openalex.org/W4296613150", "https://openalex.org/W4297813615", "https://openalex.org/W4299732308", "https://openalex.org/W4308393531", "https://openalex.org/W4308885870", "https://openalex.org/W4310645210", "https://openalex.org/W4312220150", "https://openalex.org/W4313439128", "https://openalex.org/W4313484371", "https://openalex.org/W4318071656", "https://openalex.org/W4318751307", "https://openalex.org/W4319065545", "https://openalex.org/W4319335178", "https://openalex.org/W4321459182", "https://openalex.org/W4322718246", "https://openalex.org/W4323572061", "https://openalex.org/W4361289277", "https://openalex.org/W4366163632", "https://openalex.org/W4366330503", "https://openalex.org/W4376130909", "https://openalex.org/W4376167553", "https://openalex.org/W4376643691", "https://openalex.org/W4376864533", "https://openalex.org/W4377011132", "https://openalex.org/W4377121462", "https://openalex.org/W4377226909", "https://openalex.org/W4377372369", "https://openalex.org/W4378174011", "https://openalex.org/W4378498682", "https://openalex.org/W4378509449", "https://openalex.org/W4378672794", "https://openalex.org/W4378711593", "https://openalex.org/W4379259189", "https://openalex.org/W4379918953", "https://openalex.org/W4380137126", "https://openalex.org/W4380421649", "https://openalex.org/W4380994269", "https://openalex.org/W4381786045", "https://openalex.org/W4381827575", "https://openalex.org/W4382334257", "https://openalex.org/W4382394524", "https://openalex.org/W4382403009", "https://openalex.org/W4382490702", "https://openalex.org/W4383987918", "https://openalex.org/W4384071683", "https://openalex.org/W4384133826", "https://openalex.org/W4385164288", "https://openalex.org/W4385346108", "https://openalex.org/W4385436420", "https://openalex.org/W4385474169", "https://openalex.org/W4385647263", "https://openalex.org/W4385965979", "https://openalex.org/W4386047824", "https://openalex.org/W4386052426", "https://openalex.org/W4386066385", "https://openalex.org/W4386083024", "https://openalex.org/W4386157633", "https://openalex.org/W4386168937", "https://openalex.org/W4386185396", "https://openalex.org/W4386185600", "https://openalex.org/W4386575491", "https://openalex.org/W4386655647", "https://openalex.org/W4386735541", "https://openalex.org/W4386876368", "https://openalex.org/W4386892967", "https://openalex.org/W4386893702", "https://openalex.org/W4386923268", "https://openalex.org/W4387028645", "https://openalex.org/W4387068110", "https://openalex.org/W4387210470", "https://openalex.org/W4387323474", "https://openalex.org/W4387346412", "https://openalex.org/W4387355843", "https://openalex.org/W4387381389", "https://openalex.org/W4387500346", "https://openalex.org/W4387559560", "https://openalex.org/W4387583347", "https://openalex.org/W4387634898", "https://openalex.org/W4387653139", "https://openalex.org/W4387724855", "https://openalex.org/W4387789684", "https://openalex.org/W4387809804", "https://openalex.org/W4387865285", "https://openalex.org/W4387891768", "https://openalex.org/W4387966979", "https://openalex.org/W4388430464", "https://openalex.org/W4388482284", "https://openalex.org/W4388513209", "https://openalex.org/W4388555312", "https://openalex.org/W4388685775", "https://openalex.org/W4388831047", "https://openalex.org/W4388926400", "https://openalex.org/W4388931647", "https://openalex.org/W4388962905", "https://openalex.org/W4389116614", "https://openalex.org/W4389216607", "https://openalex.org/W4389261102", "https://openalex.org/W4389502051", "https://openalex.org/W4389524012", "https://openalex.org/W4389524500", "https://openalex.org/W4389538721", "https://openalex.org/W4389664922", "https://openalex.org/W4389686112", "https://openalex.org/W4389708725", "https://openalex.org/W4389925873", "https://openalex.org/W4390041933", "https://openalex.org/W4390115208", "https://openalex.org/W4390214291", "https://openalex.org/W4390480840", "https://openalex.org/W4390490761", "https://openalex.org/W4390580666", "https://openalex.org/W4390603852", "https://openalex.org/W4390690017", "https://openalex.org/W4390783938", "https://openalex.org/W4391159225", "https://openalex.org/W4391316987", "https://openalex.org/W4391829954", "https://openalex.org/W4392019855", "https://openalex.org/W4392849937", "https://openalex.org/W4392947532", "https://openalex.org/W4393149524", "https://openalex.org/W4393178509", "https://openalex.org/W4394763992", "https://openalex.org/W4395026179", "https://openalex.org/W4395703766", "https://openalex.org/W4401070302", "https://openalex.org/W6908377304"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W4229365511", "https://openalex.org/W4211247774", "https://openalex.org/W3045462960", "https://openalex.org/W4393774512", "https://openalex.org/W4393658307", "https://openalex.org/W4286761081", "https://openalex.org/W4393731985", "https://openalex.org/W4210578026"], "abstract_inverted_index": {"In": [0], "the": [1, 92, 109, 113, 133, 140, 227, 233], "complex": [2], "and": [3, 12, 32, 43, 51, 54, 61, 68, 73, 89, 106, 129, 150, 154, 157, 196, 225], "multidimensional": [4], "field": [5], "of": [6, 24, 111, 135, 176, 199, 229, 236], "medicine,": [7], "multimodal": [8, 136, 212], "data": [9, 19, 25, 36, 39, 70, 115], "are": [10], "prevalent": [11], "crucial": [13], "for": [14, 86, 182], "informed": [15], "clinical": [16, 59, 119], "decisions.": [17], "Multimodal": [18], "span": [20], "a": [21, 126, 169, 179, 207], "broad": [22], "spectrum": [23], "types,": [26], "including": [27], "medical": [28, 93, 141, 214, 237], "images": [29], "(eg,": [30, 37, 49, 58, 65, 71], "MRI": [31], "CT": [33], "scans),": [34], "time-series": [35], "sensor": [38], "from": [40], "wearable": [41], "devices": [42], "electronic": [44], "health": [45, 186, 202], "records),": [46], "audio": [47], "recordings": [48], "heart": [50], "respiratory": [52], "sounds": [53], "patient": [55], "interviews),": [56], "text": [57], "notes": [60], "research": [62, 159, 195], "articles),": [63], "videos": [64], "surgical": [66], "procedures),": [67], "omics": [69], "genomics": [72], "proteomics).": [74], "While": [75], "advancements": [76], "in": [77, 91, 118, 139, 185, 201, 232], "large": [78], "language": [79], "models": [80], "(LLMs)": [81], "have": [82], "enabled": [83], "new": [84], "applications": [85], "knowledge": [87], "retrieval": [88], "processing": [90, 100], "field,": [94], "most": [95], "LLMs": [96, 137], "remain": [97], "limited": [98], "to": [99, 124, 167, 191], "unimodal": [101], "data,": [102], "typically": [103], "text-based": [104], "content,": [105], "often": [107], "overlook": [108], "importance": [110], "integrating": [112], "diverse": [114, 174], "modalities": [116], "encountered": [117], "practice.": [120, 215], "This": [121, 188], "paper": [122], "aims": [123, 190], "present": [125], "detailed,": [127], "practical,": [128], "solution-oriented": [130], "perspective": [131], "on": [132], "use": [134], "(M-LLMs)": [138], "field.": [142], "Our": [143], "investigation": [144], "spanned": [145], "M-LLM": [146, 238], "foundational": [147], "principles,": [148], "current": [149], "potential": [151], "applications,": [152], "technical": [153], "ethical": [155], "challenges,": [156], "future": [158, 184, 194], "directions.": [160], "By": [161], "connecting": [162], "these": [163], "elements,": [164], "we": [165], "aimed": [166], "provide": [168], "comprehensive": [170], "framework": [171], "that": [172, 218], "links": [173], "aspects": [175], "M-LLMs,": [177], "offering": [178], "unified": [180], "vision": [181], "their": [183], "care.": [187], "approach": [189], "guide": [192], "both": [193], "practical": [197], "implementations": [198], "M-LLMs": [200], "care,": [203], "positioning": [204], "them": [205], "as": [206], "paradigm": [208], "shift": [209], "toward": [210], "integrated,": [211], "data-driven": [213], "We": [216], "anticipate": [217], "this": [219], "work": [220], "will": [221], "spark": [222], "further": [223], "discussion": [224], "inspire": [226], "development": [228], "innovative": [230], "approaches": [231], "next": [234], "generation": [235], "systems.": [239]}, "counts_by_year": [{"year": 2026, "cited_by_count": 75}, {"year": 2025, "cited_by_count": 145}, {"year": 2024, "cited_by_count": 8}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2024-09-03T00:00:00"}, {"id": "https://openalex.org/W4402670135", "doi": "https://doi.org/10.18653/v1/2024.findings-acl.738", "title": "MM-LLMs: Recent Advances in MultiModal Large Language Models", "display_name": "MM-LLMs: Recent Advances in MultiModal Large Language Models", "relevance_score": 1640.1421, "publication_year": 2024, "publication_date": "2024-01-01", "ids": {"openalex": "https://openalex.org/W4402670135", "doi": "https://doi.org/10.18653/v1/2024.findings-acl.738"}, "language": "en", "primary_location": {"id": "doi:10.18653/v1/2024.findings-acl.738", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.738", "pdf_url": "https://aclanthology.org/2024.findings-acl.738.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://aclanthology.org/2024.findings-acl.738.pdf", "any_repository_has_fulltext": null}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5107436209", "display_name": "Duzhen Zhang", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Duzhen Zhang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107568519", "display_name": "Yahan Yu", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yahan Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014443478", "display_name": "Jiahua Dong", "orcid": "https://orcid.org/0000-0001-8545-4447"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jiahua Dong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107489234", "display_name": "Chenxing Li", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chenxing Li", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107489235", "display_name": "Dan Su", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Dan Su", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102757632", "display_name": "Chenhui Chu", "orcid": "https://orcid.org/0000-0001-9848-6384"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chenhui Chu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5107525619", "display_name": "Dong Yu", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Dong Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5107436209"], "corresponding_institution_ids": [], "apc_list": null, "apc_paid": null, "fwci": 61.3086, "has_fulltext": true, "cited_by_count": 194, "citation_normalized_percentile": {"value": 0.99933914, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "12401", "last_page": "12430"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9868000149726868, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.5807963013648987}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.5807963013648987}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.18653/v1/2024.findings-acl.738", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.738", "pdf_url": "https://aclanthology.org/2024.findings-acl.738.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}], "best_oa_location": {"id": "doi:10.18653/v1/2024.findings-acl.738", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.738", "pdf_url": "https://aclanthology.org/2024.findings-acl.738.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}, "sustainable_development_goals": [], "awards": [], "funders": [{"id": "https://openalex.org/F4320334764", "display_name": "Japan Society for the Promotion of Science", "ror": "https://ror.org/00hhkn466"}], "has_content": {"pdf": true, "grobid_xml": false}, "content_urls": {"pdf": "https://content.openalex.org/works/W4402670135.pdf"}, "referenced_works_count": 0, "referenced_works": [], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052", "https://openalex.org/W2382290278", "https://openalex.org/W4395014643"], "abstract_inverted_index": null, "counts_by_year": [{"year": 2026, "cited_by_count": 27}, {"year": 2025, "cited_by_count": 127}, {"year": 2024, "cited_by_count": 40}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4387583347", "doi": "https://doi.org/10.2196/52865", "title": "The Impact of Multimodal Large Language Models on Health Care\u2019s Future", "display_name": "The Impact of Multimodal Large Language Models on Health Care\u2019s Future", "relevance_score": 1610.8857, "publication_year": 2023, "publication_date": "2023-10-12", "ids": {"openalex": "https://openalex.org/W4387583347", "doi": "https://doi.org/10.2196/52865", "pmid": "https://pubmed.ncbi.nlm.nih.gov/37917126"}, "language": "en", "primary_location": {"id": "doi:10.2196/52865", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/52865", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://doi.org/10.2196/52865", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5064145018", "display_name": "Bertalan Mesk\u00f3", "orcid": "https://orcid.org/0000-0002-7005-7083"}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Bertalan Mesk\u00f3", "raw_affiliation_strings": ["The Medical Futurist Intitute, Budapest, XI., Hungary"], "raw_orcid": "https://orcid.org/0000-0002-7005-7083", "affiliations": [{"raw_affiliation_string": "The Medical Futurist Intitute, Budapest, XI., Hungary", "institution_ids": []}]}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 1, "corresponding_author_ids": ["https://openalex.org/A5064145018"], "corresponding_institution_ids": [], "apc_list": {"value": 2950, "currency": "USD", "value_usd": 2950}, "apc_paid": {"value": 2950, "currency": "USD", "value_usd": 2950}, "fwci": 6.3551, "has_fulltext": false, "cited_by_count": 175, "citation_normalized_percentile": {"value": 0.9710713, "is_in_top_1_percent": false, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 97, "max": 100}, "biblio": {"volume": "25", "issue": null, "first_page": "e52865", "last_page": "e52865"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11775", "display_name": "COVID-19 diagnosis using AI", "score": 0.9943000078201294, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10862", "display_name": "AI in cancer detection", "score": 0.9670000076293945, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/health-care", "display_name": "Health care", "score": 0.5353963971138}, {"id": "https://openalex.org/keywords/generative-grammar", "display_name": "Generative grammar", "score": 0.4516529142856598}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.3221093714237213}, {"id": "https://openalex.org/keywords/psychology", "display_name": "Psychology", "score": 0.3211050033569336}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.2929375171661377}, {"id": "https://openalex.org/keywords/economic-growth", "display_name": "Economic growth", "score": 0.0956132709980011}, {"id": "https://openalex.org/keywords/economics", "display_name": "Economics", "score": 0.09044194221496582}], "concepts": [{"id": "https://openalex.org/C160735492", "wikidata": "https://www.wikidata.org/wiki/Q31207", "display_name": "Health care", "level": 2, "score": 0.5353963971138}, {"id": "https://openalex.org/C39890363", "wikidata": "https://www.wikidata.org/wiki/Q36108", "display_name": "Generative grammar", "level": 2, "score": 0.4516529142856598}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.3221093714237213}, {"id": "https://openalex.org/C15744967", "wikidata": "https://www.wikidata.org/wiki/Q9418", "display_name": "Psychology", "level": 0, "score": 0.3211050033569336}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.2929375171661377}, {"id": "https://openalex.org/C50522688", "wikidata": "https://www.wikidata.org/wiki/Q189833", "display_name": "Economic growth", "level": 1, "score": 0.0956132709980011}, {"id": "https://openalex.org/C162324750", "wikidata": "https://www.wikidata.org/wiki/Q8134", "display_name": "Economics", "level": 0, "score": 0.09044194221496582}], "mesh": [{"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D004645", "descriptor_name": "Empathy", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D004645", "descriptor_name": "Empathy", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D004645", "descriptor_name": "Empathy", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006282", "descriptor_name": "Health Personnel", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006282", "descriptor_name": "Health Personnel", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006282", "descriptor_name": "Health Personnel", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D010817", "descriptor_name": "Physician-Patient Relations", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D010817", "descriptor_name": "Physician-Patient Relations", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D010817", "descriptor_name": "Physician-Patient Relations", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}], "locations_count": 4, "locations": [{"id": "doi:10.2196/52865", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/52865", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, {"id": "pmid:37917126", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/37917126", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of medical Internet research", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:10654899", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/10654899", "pdf_url": null, "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "J Med Internet Res", "raw_type": "Text"}, {"id": "pmh:oai:doaj.org/article:f141df4f1ded4d748aa743e350863d36", "is_oa": true, "landing_page_url": "https://doaj.org/article/f141df4f1ded4d748aa743e350863d36", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401280", "display_name": "DOAJ (DOAJ: Directory of Open Access Journals)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-sa", "license_id": "https://openalex.org/licenses/cc-by-sa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Journal of Medical Internet Research, Vol 25, p e52865 (2023)", "raw_type": "article"}], "best_oa_location": {"id": "doi:10.2196/52865", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/52865", "pdf_url": null, "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 11, "referenced_works": ["https://openalex.org/W2883790289", "https://openalex.org/W2900834200", "https://openalex.org/W3086667591", "https://openalex.org/W4214758645", "https://openalex.org/W4295951577", "https://openalex.org/W4365143687", "https://openalex.org/W4372405940", "https://openalex.org/W4383346782", "https://openalex.org/W4386504974", "https://openalex.org/W4386829267", "https://openalex.org/W4386867830"], "related_works": ["https://openalex.org/W2748952813", "https://openalex.org/W2380075625", "https://openalex.org/W4390549206", "https://openalex.org/W2931662336", "https://openalex.org/W4390718435", "https://openalex.org/W3137171911", "https://openalex.org/W2077865380", "https://openalex.org/W2765597752", "https://openalex.org/W4237784285", "https://openalex.org/W2134894512"], "abstract_inverted_index": {"When": [0], "large": [1, 11], "language": [2], "models": [3], "(LLMs)": [4], "were": [5], "introduced": [6], "to": [7, 141, 168, 213], "the": [8, 18, 33, 57, 92, 103, 122, 143, 153, 174, 181, 185, 215, 223], "public": [9], "at": [10], "in": [12, 41, 91, 101, 180, 188], "late": [13], "2022": [14], "with": [15, 22], "ChatGPT": [16], "(OpenAI),": [17], "interest": [19], "was": [20], "unprecedented,": [21], "more": [23], "than": [24, 206], "1": [25], "billion": [26], "unique": [27], "users": [28], "within": [29], "90": [30], "days.": [31], "Until": [32], "introduction": [34], "of": [35, 61, 94, 106, 112, 124, 127, 177, 183, 218], "Generative": [36], "Pre-trained": [37], "Transformer": [38], "4": [39], "(GPT-4)": [40], "March": [42], "2023,": [43], "these": [44], "LLMs": [45, 62, 149], "only": [46, 74], "contained": [47], "a": [48, 54, 88, 109, 197], "single": [49], "mode-text.": [50], "As": [51], "medicine": [52, 189], "is": [53, 166, 210], "multimodal": [55, 125, 148], "discipline,": [56], "potential": [58, 105, 144, 176], "future": [59], "versions": [60], "that": [63, 67, 114, 172, 199], "can": [64, 200], "handle": [65], "multimodality-meaning": [66], "they": [68], "could": [69, 151], "interpret": [70], "and": [71, 81, 130, 159, 222], "generate": [72], "not": [73], "text": [75], "but": [76], "also": [77, 115, 211], "images,": [78, 129], "videos,": [79], "sound,": [80], "even": [82], "comprehensive": [83], "documents-can": [84], "be": [85, 194], "conceptualized": [86], "as": [87, 119, 147, 196], "significant": [89], "evolution": [90], "field": [93], "artificial": [95], "intelligence": [96], "(AI).": [97], "This": [98], "paper": [99], "zooms": [100], "on": [102, 132], "new": [104, 110], "generative": [107, 178], "AI,": [108], "form": [111, 182], "AI": [113, 161, 179, 192], "includes": [116], "tools": [117], "such": [118], "LLMs,": [120], "through": [121], "achievement": [123], "inputs": [126], "text,": [128], "speech": [131], "health": [133, 156, 202, 219], "care's": [134], "future.": [135], "We": [136], "present": [137], "several": [138], "futuristic": [139], "scenarios": [140], "illustrate": [142], "path": [145], "forward": [146], "(M-LLMs)": [150], "represent": [152], "gateway": [154], "between": [155], "care": [157, 203], "professionals": [158, 204], "using": [160], "for": [162], "medical": [163], "purposes.": [164], "It": [165, 209], "important": [167, 212], "point": [169], "out,": [170], "though,": [171], "despite": [173], "unprecedented": [175], "M-LLMs,": [184], "human": [186, 216], "touch": [187], "remains": [190], "irreplaceable.": [191], "should": [193], "seen": [195], "tool": [198], "augment": [201], "rather": [205], "replace": [207], "them.": [208], "consider": [214], "aspects": [217], "care-empathy,": [220], "understanding,": [221], "doctor-patient": [224], "relationship-when": [225], "deploying": [226], "AI.": [227]}, "counts_by_year": [{"year": 2026, "cited_by_count": 17}, {"year": 2025, "cited_by_count": 77}, {"year": 2024, "cited_by_count": 77}, {"year": 2023, "cited_by_count": 4}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4389267014", "doi": "https://doi.org/10.1038/s41746-023-00952-2", "title": "A medical multimodal large language model for future pandemics", "display_name": "A medical multimodal large language model for future pandemics", "relevance_score": 1605.852, "publication_year": 2023, "publication_date": "2023-12-02", "ids": {"openalex": "https://openalex.org/W4389267014", "doi": "https://doi.org/10.1038/s41746-023-00952-2", "pmid": "https://pubmed.ncbi.nlm.nih.gov/38042919"}, "language": "en", "primary_location": {"id": "doi:10.1038/s41746-023-00952-2", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41746-023-00952-2", "pdf_url": "https://www.nature.com/articles/s41746-023-00952-2.pdf", "source": {"id": "https://openalex.org/S4210195431", "display_name": "npj Digital Medicine", "issn_l": "2398-6352", "issn": ["2398-6352"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "npj Digital Medicine", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://www.nature.com/articles/s41746-023-00952-2.pdf", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100632772", "display_name": "Fenglin Liu", "orcid": "https://orcid.org/0000-0001-7715-5228"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}, {"id": "https://openalex.org/I4210146410", "display_name": "Science Oxford", "ror": "https://ror.org/04j8yhy50", "country_code": "GB", "type": "nonprofit", "lineage": ["https://openalex.org/I4210146410"]}], "countries": ["GB"], "is_corresponding": true, "raw_author_name": "Fenglin Liu", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK. fenglin.liu@eng.ox.ac.uk", "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK"], "raw_orcid": "https://orcid.org/0000-0001-7715-5228", "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK. fenglin.liu@eng.ox.ac.uk", "institution_ids": ["https://openalex.org/I4210146410"]}, {"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055850985", "display_name": "Tingting Zhu", "orcid": "https://orcid.org/0000-0002-1552-5630"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Tingting Zhu", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK"], "raw_orcid": "https://orcid.org/0000-0002-1552-5630", "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100352418", "display_name": "Xian Wu", "orcid": "https://orcid.org/0000-0003-1118-9710"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xian Wu", "raw_affiliation_strings": ["Jarvis Research Center, Tencent YouTu Lab, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Jarvis Research Center, Tencent YouTu Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101695004", "display_name": "Bang Yang", "orcid": "https://orcid.org/0000-0003-2019-0377"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Bang Yang", "raw_affiliation_strings": ["School of Computer Science, Peking University, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0003-2019-0377", "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076320750", "display_name": "Chenyu You", "orcid": "https://orcid.org/0000-0001-8365-7822"}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Chenyu You", "raw_affiliation_strings": ["Yale University, New Haven, CT, USA"], "raw_orcid": "https://orcid.org/0000-0001-8365-7822", "affiliations": [{"raw_affiliation_string": "Yale University, New Haven, CT, USA", "institution_ids": ["https://openalex.org/I32971472"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100424709", "display_name": "Chenyang Wang", "orcid": "https://orcid.org/0000-0003-1851-9866"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Chenyang Wang", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK"], "raw_orcid": "https://orcid.org/0000-0003-1851-9866", "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5053733933", "display_name": "Lei L\u00fc", "orcid": "https://orcid.org/0000-0001-9139-8955"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Lei Lu", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040149528", "display_name": "Zhangdaihong Liu", "orcid": "https://orcid.org/0000-0003-2142-477X"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}, {"id": "https://openalex.org/I4210125878", "display_name": "Suzhou Research Institute", "ror": "https://ror.org/03ebk0c60", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4210125878"]}], "countries": ["CN", "GB"], "is_corresponding": false, "raw_author_name": "Zhangdaihong Liu", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "Oxford-Suzhou Centre for Advanced Research, Suzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}, {"raw_affiliation_string": "Oxford-Suzhou Centre for Advanced Research, Suzhou, China", "institution_ids": ["https://openalex.org/I4210125878"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5051649145", "display_name": "Yefeng Zheng", "orcid": "https://orcid.org/0000-0003-2195-2847"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yefeng Zheng", "raw_affiliation_strings": ["Jarvis Research Center, Tencent YouTu Lab, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0003-2195-2847", "affiliations": [{"raw_affiliation_string": "Jarvis Research Center, Tencent YouTu Lab, Beijing, China", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111863979", "display_name": "Xu Sun", "orcid": "https://orcid.org/0000-0001-5389-7251"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xu Sun", "raw_affiliation_strings": ["School of Computer Science, Peking University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100397381", "display_name": "Yang Yang", "orcid": "https://orcid.org/0000-0001-5720-773X"}, "institutions": [{"id": "https://openalex.org/I183067930", "display_name": "Shanghai Jiao Tong University", "ror": "https://ror.org/0220qvk04", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183067930"]}, {"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yang Yang", "raw_affiliation_strings": ["School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China", "School of Computer Science, Peking University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China", "institution_ids": ["https://openalex.org/I183067930"]}, {"raw_affiliation_string": "School of Computer Science, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055138562", "display_name": "Lei Clifton", "orcid": "https://orcid.org/0000-0001-5595-8468"}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Lei Clifton", "raw_affiliation_strings": ["Nuffield Department of Population Health, University of Oxford, Oxford, UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nuffield Department of Population Health, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5040302008", "display_name": "David A. Clifton", "orcid": "https://orcid.org/0000-0002-9848-8555"}, "institutions": [{"id": "https://openalex.org/I4210125878", "display_name": "Suzhou Research Institute", "ror": "https://ror.org/03ebk0c60", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4210125878"]}, {"id": "https://openalex.org/I4210146410", "display_name": "Science Oxford", "ror": "https://ror.org/04j8yhy50", "country_code": "GB", "type": "nonprofit", "lineage": ["https://openalex.org/I4210146410"]}], "countries": ["CN", "GB"], "is_corresponding": false, "raw_author_name": "David A. Clifton", "raw_affiliation_strings": ["Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK. david.clifton@eng.ox.ac.uk", "Oxford-Suzhou Centre for Advanced Research, Suzhou, China. david.clifton@eng.ox.ac.uk", "Oxford-Suzhou Centre for Advanced Research, Suzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK. david.clifton@eng.ox.ac.uk", "institution_ids": ["https://openalex.org/I4210146410"]}, {"raw_affiliation_string": "Oxford-Suzhou Centre for Advanced Research, Suzhou, China. david.clifton@eng.ox.ac.uk", "institution_ids": ["https://openalex.org/I4210125878"]}, {"raw_affiliation_string": "Oxford-Suzhou Centre for Advanced Research, Suzhou, China", "institution_ids": ["https://openalex.org/I4210125878"]}]}], "institutions": [], "countries_distinct_count": 3, "institutions_distinct_count": 13, "corresponding_author_ids": ["https://openalex.org/A5100632772"], "corresponding_institution_ids": ["https://openalex.org/I40120149", "https://openalex.org/I4210146410"], "apc_list": {"value": 3060, "currency": "USD", "value_usd": 3060}, "apc_paid": {"value": 3060, "currency": "USD", "value_usd": 3060}, "fwci": 31.1097, "has_fulltext": true, "cited_by_count": 139, "citation_normalized_percentile": {"value": 0.99874856, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "6", "issue": "1", "first_page": "226", "last_page": "226"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11775", "display_name": "COVID-19 diagnosis using AI", "score": 0.998199999332428, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11775", "display_name": "COVID-19 diagnosis using AI", "score": 0.998199999332428, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9768000245094299, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.97079998254776, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/pandemic", "display_name": "Pandemic", "score": 0.6385005116462708}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.4590938985347748}, {"id": "https://openalex.org/keywords/coronavirus-disease-2019", "display_name": "Coronavirus disease 2019 (COVID-19)", "score": 0.41384172439575195}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.32206547260284424}, {"id": "https://openalex.org/keywords/medicine", "display_name": "Medicine", "score": 0.19004371762275696}, {"id": "https://openalex.org/keywords/philosophy", "display_name": "Philosophy", "score": 0.10929378867149353}, {"id": "https://openalex.org/keywords/infectious-disease", "display_name": "Infectious disease (medical specialty)", "score": 0.07089638710021973}, {"id": "https://openalex.org/keywords/disease", "display_name": "Disease", "score": 0.06941449642181396}], "concepts": [{"id": "https://openalex.org/C89623803", "wikidata": "https://www.wikidata.org/wiki/Q12184", "display_name": "Pandemic", "level": 5, "score": 0.6385005116462708}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.4590938985347748}, {"id": "https://openalex.org/C3008058167", "wikidata": "https://www.wikidata.org/wiki/Q84263196", "display_name": "Coronavirus disease 2019 (COVID-19)", "level": 4, "score": 0.41384172439575195}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.32206547260284424}, {"id": "https://openalex.org/C71924100", "wikidata": "https://www.wikidata.org/wiki/Q11190", "display_name": "Medicine", "level": 0, "score": 0.19004371762275696}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.10929378867149353}, {"id": "https://openalex.org/C524204448", "wikidata": "https://www.wikidata.org/wiki/Q788926", "display_name": "Infectious disease (medical specialty)", "level": 3, "score": 0.07089638710021973}, {"id": "https://openalex.org/C2779134260", "wikidata": "https://www.wikidata.org/wiki/Q12136", "display_name": "Disease", "level": 2, "score": 0.06941449642181396}, {"id": "https://openalex.org/C142724271", "wikidata": "https://www.wikidata.org/wiki/Q7208", "display_name": "Pathology", "level": 1, "score": 0.0}], "mesh": [], "locations_count": 7, "locations": [{"id": "doi:10.1038/s41746-023-00952-2", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41746-023-00952-2", "pdf_url": "https://www.nature.com/articles/s41746-023-00952-2.pdf", "source": {"id": "https://openalex.org/S4210195431", "display_name": "npj Digital Medicine", "issn_l": "2398-6352", "issn": ["2398-6352"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "npj Digital Medicine", "raw_type": "journal-article"}, {"id": "pmid:38042919", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/38042919", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "NPJ digital medicine", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:10693607", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/10693607", "pdf_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10693607/pdf/41746_2023_Article_952.pdf", "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "NPJ Digit Med", "raw_type": "Text"}, {"id": "pmh:oai:doaj.org/article:8660a4c9237d4be09546ee7d024c40bd", "is_oa": true, "landing_page_url": "https://doaj.org/article/8660a4c9237d4be09546ee7d024c40bd", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401280", "display_name": "DOAJ (DOAJ: Directory of Open Access Journals)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-sa", "license_id": "https://openalex.org/licenses/cc-by-sa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "npj Digital Medicine, Vol 6, Iss 1, Pp 1-15 (2023)", "raw_type": "article"}, {"id": "pmh:oai:kclpure.kcl.ac.uk:openaire/67921753-ed3c-42ca-b9f4-9b9e3cdf68cc", "is_oa": true, "landing_page_url": "https://www.scopus.com/pages/publications/85178392232", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400216", "display_name": "Research Portal (King's College London)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I183935753", "host_organization_name": "King's College London", "host_organization_lineage": ["https://openalex.org/I183935753"], "host_organization_lineage_names": [], "type": "repository"}, "license": "other-oa", "license_id": "https://openalex.org/licenses/other-oa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Liu, F, Zhu, T, Wu, X, Yang, B, You, C, Wang, C, Lu, L, Liu, Z, Zheng, Y, Sun, X, Yang, Y, Clifton, L & Clifton, D A 2023, 'A medical multimodal large language model for future pandemics', npj Digital Medicine, vol. 6, no. 1, 226. https://doi.org/10.1038/s41746-023-00952-2", "raw_type": "info:eu-repo/semantics/publishedVersion"}, {"id": "pmh:oai:kclpure.kcl.ac.uk:publications/67921753-ed3c-42ca-b9f4-9b9e3cdf68cc", "is_oa": true, "landing_page_url": "https://kclpure.kcl.ac.uk/portal/en/publications/67921753-ed3c-42ca-b9f4-9b9e3cdf68cc", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400216", "display_name": "Research Portal (King's College London)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I183935753", "host_organization_name": "King's College London", "host_organization_lineage": ["https://openalex.org/I183935753"], "host_organization_lineage_names": [], "type": "repository"}, "license": "other-oa", "license_id": "https://openalex.org/licenses/other-oa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Liu, F, Zhu, T, Wu, X, Yang, B, You, C, Wang, C, Lu, L, Liu, Z, Zheng, Y, Sun, X, Yang, Y, Clifton, L & Clifton, D A 2023, 'A medical multimodal large language model for future pandemics', npj Digital Medicine, vol. 6, no. 1, 226. https://doi.org/10.1038/s41746-023-00952-2", "raw_type": "info:eu-repo/semantics/publishedVersion"}, {"id": "pmh:oai:ora.ox.ac.uk:uuid:dc358e68-1be1-4c7b-a478-7e0023fda5c5", "is_oa": true, "landing_page_url": "https://ora.ox.ac.uk/objects/uuid:dc358e68-1be1-4c7b-a478-7e0023fda5c5", "pdf_url": null, "source": {"id": "https://openalex.org/S4306402636", "display_name": "Oxford University Research Archive (ORA) (University of Oxford)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I40120149", "host_organization_name": "University of Oxford", "host_organization_lineage": ["https://openalex.org/I40120149"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Symplectic Elements", "raw_type": "Journal article"}], "best_oa_location": {"id": "doi:10.1038/s41746-023-00952-2", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41746-023-00952-2", "pdf_url": "https://www.nature.com/articles/s41746-023-00952-2.pdf", "source": {"id": "https://openalex.org/S4210195431", "display_name": "npj Digital Medicine", "issn_l": "2398-6352", "issn": ["2398-6352"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "npj Digital Medicine", "raw_type": "journal-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/3", "score": 0.7599999904632568, "display_name": "Good health and well-being"}], "awards": [], "funders": [{"id": "https://openalex.org/F4320319990", "display_name": "National Institute for Health and Care Research", "ror": "https://ror.org/0187kwz08"}, {"id": "https://openalex.org/F4320320005", "display_name": "Royal Academy of Engineering", "ror": "https://ror.org/0526snb40"}, {"id": "https://openalex.org/F4320320290", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110"}, {"id": "https://openalex.org/F4320336045", "display_name": "NIHR Oxford Biomedical Research Centre", "ror": null}, {"id": "https://openalex.org/F4320336183", "display_name": "Clarendon Fund", "ror": null}], "has_content": {"pdf": true, "grobid_xml": false}, "content_urls": {"pdf": "https://content.openalex.org/works/W4389267014.pdf"}, "referenced_works_count": 94, "referenced_works": ["https://openalex.org/W1889081078", "https://openalex.org/W1904878066", "https://openalex.org/W1956340063", "https://openalex.org/W2040246121", "https://openalex.org/W2101105183", "https://openalex.org/W2108598243", "https://openalex.org/W2122402213", "https://openalex.org/W2159583324", "https://openalex.org/W2177066871", "https://openalex.org/W2194775991", "https://openalex.org/W2396881363", "https://openalex.org/W2515682654", "https://openalex.org/W2581082771", "https://openalex.org/W2611650229", "https://openalex.org/W2770165365", "https://openalex.org/W2778310824", "https://openalex.org/W2789303506", "https://openalex.org/W2857887762", "https://openalex.org/W2911489562", "https://openalex.org/W2914203365", "https://openalex.org/W2963373823", "https://openalex.org/W2963466845", "https://openalex.org/W2963716420", "https://openalex.org/W2963967185", "https://openalex.org/W2964744899", "https://openalex.org/W2965373594", "https://openalex.org/W2970971581", "https://openalex.org/W2971258845", "https://openalex.org/W2980282514", "https://openalex.org/W2995225687", "https://openalex.org/W3006082171", "https://openalex.org/W3008627141", "https://openalex.org/W3008985036", "https://openalex.org/W3013507463", "https://openalex.org/W3014561994", "https://openalex.org/W3016836174", "https://openalex.org/W3017855299", "https://openalex.org/W3033814865", "https://openalex.org/W3035524453", "https://openalex.org/W3046375318", "https://openalex.org/W3074741277", "https://openalex.org/W3092603779", "https://openalex.org/W3094502228", "https://openalex.org/W3094894162", "https://openalex.org/W3094948156", "https://openalex.org/W3095681026", "https://openalex.org/W3095828274", "https://openalex.org/W3098325931", "https://openalex.org/W3101156210", "https://openalex.org/W3104609094", "https://openalex.org/W3114062942", "https://openalex.org/W3119527628", "https://openalex.org/W3129875423", "https://openalex.org/W3129922404", "https://openalex.org/W3132450979", "https://openalex.org/W3134475970", "https://openalex.org/W3135057764", "https://openalex.org/W3135367836", "https://openalex.org/W3136933888", "https://openalex.org/W3138497854", "https://openalex.org/W3139487216", "https://openalex.org/W3154493450", "https://openalex.org/W3160840375", "https://openalex.org/W3162351260", "https://openalex.org/W3164323420", "https://openalex.org/W3174714208", "https://openalex.org/W3177048142", "https://openalex.org/W3181252431", "https://openalex.org/W3189279073", "https://openalex.org/W3201906559", "https://openalex.org/W3212101459", "https://openalex.org/W3213233983", "https://openalex.org/W4221143046", "https://openalex.org/W4230649743", "https://openalex.org/W4247493843", "https://openalex.org/W4285531589", "https://openalex.org/W4292947664", "https://openalex.org/W4296027312", "https://openalex.org/W4310266197", "https://openalex.org/W4312220150", "https://openalex.org/W4312420429", "https://openalex.org/W4312533035", "https://openalex.org/W4318069287", "https://openalex.org/W4318408278", "https://openalex.org/W4318925155", "https://openalex.org/W4362603432", "https://openalex.org/W4377009978", "https://openalex.org/W4384071683", "https://openalex.org/W4385573131", "https://openalex.org/W6739901393", "https://openalex.org/W6760721734", "https://openalex.org/W6778883912", "https://openalex.org/W6804012510", "https://openalex.org/W6986955575"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2899084033", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W4205698903", "https://openalex.org/W4400613637", "https://openalex.org/W4391913857", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W3046517191"], "abstract_inverted_index": {"Deep": [0], "neural": [1, 28], "networks": [2, 29], "have": [3], "been": [4], "integrated": [5], "into": [6], "the": [7, 15, 21, 37, 149, 161, 167, 172, 175, 181, 186, 189], "whole": [8], "clinical": [9, 81, 130, 138], "decision": [10], "procedure": [11], "which": [12, 69], "can": [13, 70, 96, 134, 236], "improve": [14], "efficiency": [16], "of": [17, 24, 41, 151, 201, 207], "diagnosis": [18], "and": [19, 39, 80, 100, 120, 122, 128, 144, 179, 214, 220, 228, 239], "alleviate": [20], "heavy": [22], "workload": [23], "physicians.": [25], "Since": [26], "most": [27], "are": [30, 195], "supervised,": [31], "their": [32], "performance": [33], "heavily": [34], "depends": [35], "on": [36, 174, 188, 197], "volume": [38], "quality": [40], "available": [42], "labels.": [43, 107], "However,": [44], "few": [45], "such": [46], "labels": [47], "exist": [48], "for": [49, 65, 137], "rare": [50, 92], "diseases": [51], "(e.g.,": [52, 75, 117, 125], "new": [53, 190], "pandemics).": [54], "Here": [55], "we": [56, 170, 184], "report": [57, 127], "a": [58, 87, 91], "medical": [59, 73, 112, 126], "multimodal": [60], "large": [61], "language": [62], "model": [63, 110, 173, 187, 235], "(Med-MLLM)": [64], "radiograph": [66], "representation": [67], "learning,": [68], "learn": [71], "broad": [72], "knowledge": [74], "image": [76], "understanding,": [77], "text": [78], "semantics,": [79], "phenotypes)": [82], "from": [83], "unlabelled": [84], "data.": [85, 146, 246], "As": [86], "result,": [88], "when": [89], "encountering": [90], "disease,": [93], "our": [94, 109, 152, 234], "Med-MLLM": [95, 153], "be": [97, 135], "rapidly": [98], "deployed": [99], "easily": [101], "adapted": [102], "to": [103], "them": [104], "with": [105, 243], "limited": [106], "Furthermore,": [108], "supports": [111], "data": [113], "across": [114], "visual": [115, 143], "modality": [116, 124], "chest": [118], "X-ray": [119], "CT)": [121], "textual": [123, 145], "free-text": [129], "note);": [131], "therefore,": [132], "it": [133, 157], "used": [136], "tasks": [139], "that": [140, 233], "involve": [141], "both": [142], "We": [147], "demonstrate": [148], "effectiveness": [150], "by": [154], "showing": [155], "how": [156], "would": [158], "perform": [159], "using": [160], "COVID-19": [162, 177, 218, 241], "pandemic": [163], "\"in": [164], "replay\".": [165], "In": [166], "retrospective": [168], "setting,": [169, 183], "test": [171, 185], "early": [176], "datasets;": [178, 219], "in": [180], "prospective": [182], "variant": [191], "COVID-19-Omicron.": [192], "The": [193], "experiments": [194, 231], "conducted": [196], "1)": [198], "three": [199, 205, 222], "kinds": [200, 206], "input": [202], "data;": [203], "2)": [204], "downstream": [208], "tasks,": [209], "including": [210, 225], "disease": [211], "reporting,": [212], "diagnosis,": [213], "prognosis;": [215], "3)": [216], "five": [217], "4)": [221], "different": [223], "languages,": [224], "English,": [226], "Chinese,": [227], "Spanish.": [229], "All": [230], "show": [232], "make": [237], "accurate": [238], "robust": [240], "decision-support": [242], "little": [244], "labelled": [245]}, "counts_by_year": [{"year": 2026, "cited_by_count": 21}, {"year": 2025, "cited_by_count": 80}, {"year": 2024, "cited_by_count": 38}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4382490555", "doi": "https://doi.org/10.48550/arxiv.2306.14824", "title": "Kosmos-2: Grounding Multimodal Large Language Models to the World", "display_name": "Kosmos-2: Grounding Multimodal Large Language Models to the World", "relevance_score": 1540.4491, "publication_year": 2023, "publication_date": "2023-06-26", "ids": {"openalex": "https://openalex.org/W4382490555", "doi": "https://doi.org/10.48550/arxiv.2306.14824"}, "language": "en", "primary_location": {"id": "pmh:oai:arXiv.org:2306.14824", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.14824", "pdf_url": "https://arxiv.org/pdf/2306.14824", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "", "raw_type": "text"}, "type": "preprint", "indexed_in": ["arxiv", "datacite"], "open_access": {"is_oa": true, "oa_status": "green", "oa_url": "https://arxiv.org/pdf/2306.14824", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5087043298", "display_name": "Zhiliang Peng", "orcid": "https://orcid.org/0009-0003-1120-0729"}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Peng, Zhiliang", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100370074", "display_name": "Wenhui Wang", "orcid": "https://orcid.org/0000-0002-3434-5002"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Wenhui", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5092355398", "display_name": "Li Dong", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Dong, Li", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102309890", "display_name": "Yaru Hao", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hao, Yaru", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061624006", "display_name": "Shaohan Huang", "orcid": "https://orcid.org/0000-0003-4324-6337"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Huang, Shaohan", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113130010", "display_name": "Shuming Ma", "orcid": "https://orcid.org/0000-0003-1091-1206"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ma, Shuming", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5014662947", "display_name": "Furu Wei", "orcid": "https://orcid.org/0000-0002-7810-5852"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wei, Furu", "raw_affiliation_strings": [], "affiliations": []}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5087043298"], "corresponding_institution_ids": [], "apc_list": null, "apc_paid": null, "fwci": null, "has_fulltext": true, "cited_by_count": 130, "citation_normalized_percentile": null, "cited_by_percentile_year": null, "biblio": {"volume": null, "issue": null, "first_page": null, "last_page": null}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9995999932289124, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9995999932289124, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9944000244140625, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9929999709129333, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.7664210200309753}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.5327123999595642}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.5233342051506042}, {"id": "https://openalex.org/keywords/context", "display_name": "Context (archaeology)", "score": 0.4504117965698242}, {"id": "https://openalex.org/keywords/object", "display_name": "Object (grammar)", "score": 0.4216850996017456}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.7664210200309753}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.5327123999595642}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.5233342051506042}, {"id": "https://openalex.org/C2779343474", "wikidata": "https://www.wikidata.org/wiki/Q3109175", "display_name": "Context (archaeology)", "level": 2, "score": 0.4504117965698242}, {"id": "https://openalex.org/C2781238097", "wikidata": "https://www.wikidata.org/wiki/Q175026", "display_name": "Object (grammar)", "level": 2, "score": 0.4216850996017456}, {"id": "https://openalex.org/C86803240", "wikidata": "https://www.wikidata.org/wiki/Q420", "display_name": "Biology", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C151730666", "wikidata": "https://www.wikidata.org/wiki/Q7205", "display_name": "Paleontology", "level": 1, "score": 0.0}], "mesh": [], "locations_count": 2, "locations": [{"id": "pmh:oai:arXiv.org:2306.14824", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.14824", "pdf_url": "https://arxiv.org/pdf/2306.14824", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "", "raw_type": "text"}, {"id": "doi:10.48550/arxiv.2306.14824", "is_oa": true, "landing_page_url": "https://doi.org/10.48550/arxiv.2306.14824", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": null, "is_accepted": false, "is_published": null, "raw_source_name": null, "raw_type": "article"}], "best_oa_location": {"id": "pmh:oai:arXiv.org:2306.14824", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.14824", "pdf_url": "https://arxiv.org/pdf/2306.14824", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "", "raw_type": "text"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.7300000190734863, "display_name": "Quality Education"}], "awards": [], "funders": [], "has_content": {"pdf": true, "grobid_xml": true}, "content_urls": {"pdf": "https://content.openalex.org/works/W4382490555.pdf", "grobid_xml": "https://content.openalex.org/works/W4382490555.grobid-xml"}, "referenced_works_count": 0, "referenced_works": [], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W2382290278", "https://openalex.org/W4391913857", "https://openalex.org/W2350741829", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"We": [0, 91], "introduce": [1], "Kosmos-2,": [2], "a": [3, 95, 158], "Multimodal": [4], "Large": [5], "Language": [6], "Model": [7], "(MLLM),": [8], "enabling": [9], "new": [10], "capabilities": [11, 70], "of": [12, 44, 55, 71, 98, 138, 148], "perceiving": [13, 74], "object": [14, 40], "descriptions": [15, 41], "(e.g.,": [16, 73], "bounding": [17], "boxes)": [18], "and": [19, 79, 109, 123, 127, 141, 153, 166], "grounding": [20, 86], "text": [21], "to": [22, 61, 67], "the": [23, 63, 68, 85, 133, 136, 145], "visual": [24], "world.": [25], "Specifically,": [26], "we": [27, 51], "represent": [28], "refer": [29], "expressions": [30], "as": [31, 105, 116], "links": [32], "in": [33], "Markdown,": [34], "i.e.,": [35], "``[text": [36], "span](bounding": [37], "boxes)'',": [38], "where": [39], "are": [42, 169], "sequences": [43], "location": [45], "tokens.": [46], "Together": [47], "with": [48], "multimodal": [49, 102, 113, 150], "corpora,": [50], "construct": [52], "large-scale": [53], "data": [54], "grounded": [56], "image-text": [57], "pairs": [58], "(called": [59], "GrIT)": [60], "train": [62], "model.": [64], "In": [65], "addition": [66], "existing": [69], "MLLMs": [72], "general": [75, 163], "modalities,": [76], "following": [77], "instructions,": [78], "performing": [80], "in-context": [81], "learning),": [82], "Kosmos-2": [83, 93], "integrates": [84], "capability": [87], "into": [88], "downstream": [89], "applications.": [90], "evaluate": [92], "on": [94, 144], "wide": [96], "range": [97], "tasks,": [99, 122], "including": [100], "(i)": [101], "grounding,": [103, 111], "such": [104, 115], "referring": [106, 117], "expression": [107, 118], "comprehension,": [108], "phrase": [110], "(ii)": [112], "referring,": [114], "generation,": [119], "(iii)": [120], "perception-language": [121], "(iv)": [124], "language": [125], "understanding": [126], "generation.": [128], "This": [129], "work": [130], "lays": [131], "out": [132], "foundation": [134], "for": [135], "development": [137], "Embodiment": [139], "AI": [140], "sheds": [142], "light": [143], "big": [146], "convergence": [147], "language,": [149], "perception,": [151], "action,": [152], "world": [154], "modeling,": [155], "which": [156], "is": [157], "key": [159], "step": [160], "toward": [161], "artificial": [162], "intelligence.": [164], "Code": [165], "pretrained": [167], "models": [168], "available": [170], "at": [171], "https://aka.ms/kosmos-2.": [172]}, "counts_by_year": [{"year": 2026, "cited_by_count": 1}, {"year": 2025, "cited_by_count": 22}, {"year": 2024, "cited_by_count": 95}, {"year": 2023, "cited_by_count": 12}], "updated_date": "2026-03-09T08:58:05.943551", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4382132560", "doi": "https://doi.org/10.48550/arxiv.2306.13549", "title": "A Survey on Multimodal Large Language Models", "display_name": "A Survey on Multimodal Large Language Models", "relevance_score": 1475.9594, "publication_year": 2023, "publication_date": "2023-06-23", "ids": {"openalex": "https://openalex.org/W4382132560", "doi": "https://doi.org/10.48550/arxiv.2306.13549"}, "language": "en", "primary_location": {"id": "pmh:oai:arXiv.org:2306.13549", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.13549", "pdf_url": "https://arxiv.org/pdf/2306.13549", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "type": "preprint", "indexed_in": ["arxiv", "datacite"], "open_access": {"is_oa": true, "oa_status": "green", "oa_url": "https://arxiv.org/pdf/2306.13549", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073775343", "display_name": "Shukang Yin", "orcid": "https://orcid.org/0000-0002-5356-1800"}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Yin, Shukang", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014172220", "display_name": "Chaoyou Fu", "orcid": "https://orcid.org/0000-0002-0079-7668"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fu, Chaoyou", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100572538", "display_name": "Sirui Zhao", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Sirui", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100343450", "display_name": "Ke Li", "orcid": "https://orcid.org/0000-0001-7200-4244"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Ke", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100388508", "display_name": "Xing Sun", "orcid": "https://orcid.org/0000-0002-7683-4517"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Xing", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5060550824", "display_name": "Tong Bill Xu", "orcid": "https://orcid.org/0000-0001-6186-5460"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Tong", "raw_affiliation_strings": [], "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048237545", "display_name": "Enhong Chen", "orcid": "https://orcid.org/0000-0002-4835-4102"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Enhong", "raw_affiliation_strings": [], "affiliations": []}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5073775343"], "corresponding_institution_ids": [], "apc_list": null, "apc_paid": null, "fwci": null, "has_fulltext": true, "cited_by_count": 85, "citation_normalized_percentile": null, "cited_by_percentile_year": null, "biblio": {"volume": null, "issue": null, "first_page": null, "last_page": null}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9248999953269958, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.47098347544670105}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.37122589349746704}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.3573322892189026}, {"id": "https://openalex.org/keywords/philosophy", "display_name": "Philosophy", "score": 0.1193113923072815}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.47098347544670105}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.37122589349746704}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.3573322892189026}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.1193113923072815}], "mesh": [], "locations_count": 2, "locations": [{"id": "pmh:oai:arXiv.org:2306.13549", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.13549", "pdf_url": "https://arxiv.org/pdf/2306.13549", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, {"id": "doi:10.48550/arxiv.2306.13549", "is_oa": true, "landing_page_url": "https://doi.org/10.48550/arxiv.2306.13549", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": null, "raw_source_name": null, "raw_type": "article-journal"}], "best_oa_location": {"id": "pmh:oai:arXiv.org:2306.13549", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2306.13549", "pdf_url": "https://arxiv.org/pdf/2306.13549", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.8500000238418579, "display_name": "Quality Education"}], "awards": [], "funders": [], "has_content": {"pdf": true, "grobid_xml": true}, "content_urls": {"pdf": "https://content.openalex.org/works/W4382132560.pdf", "grobid_xml": "https://content.openalex.org/works/W4382132560.grobid-xml"}, "referenced_works_count": 0, "referenced_works": [], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W2382290278", "https://openalex.org/W2478288626", "https://openalex.org/W4391913857", "https://openalex.org/W2350741829"], "abstract_inverted_index": {"Recently,": [0], "Multimodal": [1, 158, 161], "Large": [2, 19], "Language": [3, 20], "Model": [4], "(MLLM)": [5], "represented": [6], "by": [7], "GPT-4V": [8], "has": [9, 193], "been": [10], "a": [11, 24, 54, 88], "new": [12], "rising": [13], "research": [14, 86, 133, 181], "hotspot,": [15], "which": [16], "uses": [17], "powerful": [18], "Models": [21], "(LLMs)": [22], "as": [23, 37, 126, 128], "brain": [25], "to": [26, 57, 70, 96, 141], "perform": [27], "multimodal": [28, 51, 152], "tasks.": [29], "The": [30], "surprising": [31, 89], "emergent": [32], "capabilities": [33], "of": [34, 85, 103, 106, 113, 185, 191], "MLLM,": [35], "such": [36], "writing": [38], "stories": [39], "based": [40], "on": [41], "images": [42], "and": [43, 66, 98, 115, 124, 147, 154, 164, 177, 203], "OCR-free": [44], "math": [45], "reasoning,": [46], "are": [47], "rare": [48], "in": [49], "traditional": [50], "methods,": [52], "suggesting": [53], "potential": [55], "path": [56], "artificial": [58], "general": [59], "intelligence.": [60], "To": [61, 169], "this": [62, 92, 201], "end,": [63], "both": [64], "academia": [65], "industry": [67], "have": [68], "endeavored": [69], "develop": [71], "MLLMs": [72, 137], "that": [73, 188], "can": [74, 138, 206], "compete": [75], "with": [76, 151], "or": [77], "even": [78], "better": [79], "than": [80], "GPT-4V,": [81], "pushing": [82], "the": [83, 100, 110, 171, 186, 189, 215], "limit": [84], "at": [87, 220], "speed.": [90], "In": [91, 183], "paper,": [93, 172], "we": [94, 108, 131, 173, 197], "aim": [95], "trace": [97], "summarize": [99], "recent": [101], "progress": [102], "MLLMs.": [104], "First": [105], "all,": [107], "present": [109], "basic": [111], "formulation": [112], "MLLM": [114, 192], "delineate": [116], "its": [117], "related": [118], "concepts,": [119], "including": [120, 157], "architecture,": [121], "training": [122], "strategy": [123], "data,": [125], "well": [127], "evaluation.": [129], "Then,": [130], "introduce": [132], "topics": [134], "about": [135], "how": [136], "be": [139], "extended": [140, 155], "support": [142], "more": [143, 208], "granularity,": [144], "modalities,": [145], "languages,": [146], "scenarios.": [148], "We": [149], "continue": [150], "hallucination": [153], "techniques,": [156], "ICL": [159], "(M-ICL),": [160], "CoT": [162], "(M-CoT),": [163], "LLM-Aided": [165], "Visual": [166], "Reasoning": [167], "(LAVR).": [168], "conclude": [170], "discuss": [174], "existing": [175], "challenges": [176], "point": [178], "out": [179], "promising": [180], "directions.": [182], "light": [184], "fact": [187], "era": [190], "only": [194], "just": [195], "begun,": [196], "will": [198], "keep": [199], "updating": [200], "survey": [202], "hope": [204], "it": [205], "inspire": [207], "research.": [209], "An": [210], "associated": [211], "GitHub": [212], "link": [213], "collecting": [214], "latest": [216], "papers": [217], "is": [218], "available": [219], "https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models.": [221]}, "counts_by_year": [{"year": 2026, "cited_by_count": 2}, {"year": 2025, "cited_by_count": 24}, {"year": 2024, "cited_by_count": 47}, {"year": 2023, "cited_by_count": 12}], "updated_date": "2026-03-20T23:20:44.827607", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402716381", "doi": "https://doi.org/10.1109/cvpr52733.2024.01263", "title": "SEED-Bench: Benchmarking Multimodal Large Language Models", "display_name": "SEED-Bench: Benchmarking Multimodal Large Language Models", "relevance_score": 1384.476, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402716381", "doi": "https://doi.org/10.1109/cvpr52733.2024.01263"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.01263", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01263", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102004554", "display_name": "Bohao Li", "orcid": "https://orcid.org/0000-0001-7354-2116"}, "institutions": [{"id": "https://openalex.org/I4210116924", "display_name": "Chinese University of Hong Kong, Shenzhen", "ror": "https://ror.org/02d5ks197", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I177725633", "https://openalex.org/I180726961", "https://openalex.org/I4210116924"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Bohao Li", "raw_affiliation_strings": ["School of Data Science, The Chinese University of HongKong,Shenzhen"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Data Science, The Chinese University of HongKong,Shenzhen", "institution_ids": ["https://openalex.org/I4210116924"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062830848", "display_name": "Yuying Ge", "orcid": "https://orcid.org/0000-0001-5818-2589"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuying Ge", "raw_affiliation_strings": ["Tencent AI Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent AI Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5047802386", "display_name": "Yixiao Ge", "orcid": "https://orcid.org/0000-0002-5351-5329"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yixiao Ge", "raw_affiliation_strings": ["Tencent AI Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent AI Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079874882", "display_name": "Guangzhi Wang", "orcid": "https://orcid.org/0000-0002-4677-1041"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Guangzhi Wang", "raw_affiliation_strings": ["ARC Lab, Tencent PCG"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "ARC Lab, Tencent PCG", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115596056", "display_name": "Rui Wang", "orcid": "https://orcid.org/0009-0007-8089-7653"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Rui Wang", "raw_affiliation_strings": ["Tencent AI Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent AI Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003608795", "display_name": "Ruimao Zhang", "orcid": "https://orcid.org/0000-0001-9511-7532"}, "institutions": [{"id": "https://openalex.org/I4210116924", "display_name": "Chinese University of Hong Kong, Shenzhen", "ror": "https://ror.org/02d5ks197", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I177725633", "https://openalex.org/I180726961", "https://openalex.org/I4210116924"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ruimao Zhang", "raw_affiliation_strings": ["School of Data Science, The Chinese University of HongKong,Shenzhen"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Data Science, The Chinese University of HongKong,Shenzhen", "institution_ids": ["https://openalex.org/I4210116924"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5102004349", "display_name": "Ying Shan", "orcid": "https://orcid.org/0000-0001-7673-8325"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ying Shan", "raw_affiliation_strings": ["Tencent AI Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tencent AI Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5102004554"], "corresponding_institution_ids": ["https://openalex.org/I4210116924"], "apc_list": null, "apc_paid": null, "fwci": 33.2164, "has_fulltext": false, "cited_by_count": 103, "citation_normalized_percentile": {"value": 0.99819564, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "13299", "last_page": "13308"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9993000030517578, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13910", "display_name": "Computational and Text Analysis Methods", "score": 0.9605000019073486, "subfield": {"id": "https://openalex.org/subfields/3300", "display_name": "General Social Sciences"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/benchmarking", "display_name": "Benchmarking", "score": 0.8006609678268433}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6905812621116638}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.532813310623169}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.43323689699172974}, {"id": "https://openalex.org/keywords/business", "display_name": "Business", "score": 0.059057652950286865}], "concepts": [{"id": "https://openalex.org/C86251818", "wikidata": "https://www.wikidata.org/wiki/Q816754", "display_name": "Benchmarking", "level": 2, "score": 0.8006609678268433}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6905812621116638}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.532813310623169}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.43323689699172974}, {"id": "https://openalex.org/C144133560", "wikidata": "https://www.wikidata.org/wiki/Q4830453", "display_name": "Business", "level": 0, "score": 0.059057652950286865}, {"id": "https://openalex.org/C162853370", "wikidata": "https://www.wikidata.org/wiki/Q39809", "display_name": "Marketing", "level": 1, "score": 0.0}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.01263", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01263", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 40, "referenced_works": ["https://openalex.org/W3201174429", "https://openalex.org/W4292779060", "https://openalex.org/W4307079201", "https://openalex.org/W4318718936", "https://openalex.org/W4322718191", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4367628410", "https://openalex.org/W4375869762", "https://openalex.org/W4376122449", "https://openalex.org/W4376167553", "https://openalex.org/W4376312115", "https://openalex.org/W4376653374", "https://openalex.org/W4378464424", "https://openalex.org/W4378711593", "https://openalex.org/W4380136538", "https://openalex.org/W4380558379", "https://openalex.org/W4380559123", "https://openalex.org/W4380994594", "https://openalex.org/W4382142077", "https://openalex.org/W4382490555", "https://openalex.org/W4382763281", "https://openalex.org/W4384112212", "https://openalex.org/W4384268538", "https://openalex.org/W4384644210", "https://openalex.org/W4385645323", "https://openalex.org/W4385681794", "https://openalex.org/W4385848663", "https://openalex.org/W4386384924", "https://openalex.org/W4386556027", "https://openalex.org/W4386655647", "https://openalex.org/W4386942465", "https://openalex.org/W4387156669", "https://openalex.org/W4387322912", "https://openalex.org/W4387436689", "https://openalex.org/W4402671548", "https://openalex.org/W6778883912", "https://openalex.org/W6791353385", "https://openalex.org/W6849177959"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W4238897586", "https://openalex.org/W435179959", "https://openalex.org/W2619091065", "https://openalex.org/W2059640416", "https://openalex.org/W1490753184", "https://openalex.org/W2284465472", "https://openalex.org/W2291782699", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"Multimodal": [0], "large": [1, 11], "language": [2, 12], "models": [3, 13], "(MLLMs),": [4], "building": [5], "upon": [6], "the": [7, 62, 74, 78, 88, 105, 120, 140, 168, 180, 193, 214], "foundation": [8], "of": [9, 36, 53, 80, 90, 123, 142, 164, 182, 195, 216], "powerful": [10], "(LLMs),": [14], "have": [15], "recently": [16], "demonstrated": [17], "exceptional": [18], "capabilities": [19, 89], "in": [20, 65], "generating": [21], "not": [22], "only": [23, 49], "texts": [24], "but": [25], "also": [26], "images": [27], "given": [28], "in-terleaved": [29], "multimodal": [30], "inputs": [31], "(acting": [32], "like": [33], "a": [34, 115], "combination": [35], "GPT-4V": [37], "and": [38, 76, 110, 112, 145, 161, 187, 221], "DALL-E": [39], "3).": [40], "However,": [41], "existing": [42, 196], "MLLM": [43], "benchmarks": [44], "remain": [45], "limited": [46], "to": [47, 58, 99, 205], "assessing": [48], "models'": [50], "comprehension": [51], "ability": [52], "single": [54], "image-text": [55], "inputs,": [56], "failing": [57], "keep": [59], "up": [60], "with": [61, 131, 150], "strides": [63], "made": [64], "MLLMs.": [66, 82, 124], "A": [67], "comprehensive": [68, 116], "benchmark": [69, 117], "is": [70], "imperative": [71], "for": [72, 170, 203], "investigating": [73], "progress": [75], "uncovering": [77], "limitations": [79, 194], "current": [81], "In": [83], "this": [84], "work,": [85], "we": [86, 201], "categorize": [87], "MLLMs": [91, 186, 197], "into": [92], "hierarchical": [93, 121], "levels": [94], "from": [95, 155], "L<inf": [96, 100], "xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"": [97, 101], "xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>": [98], "xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</inf>": [102], "based": [103], "on": [104], "modalities": [106], "they": [107], "can": [108], "ac-cept": [109], "generate,": [111], "propose": [113], "SEED-Bench,": [114], "that": [118, 208], "evaluates": [119], "capa-bilities": [122], "Specifically,": [125], "SEED-Bench": [126, 204], "comprises": [127], "24K": [128], "multiple-choice": [129], "questions": [130, 149], "accurate": [132], "human": [133, 156, 171], "annotations,": [134], "which": [135], "span": [136], "27": [137], "dimensions,": [138], "including": [139], "evaluation": [141, 222], "both": [143], "text": [144], "image": [146], "generation.": [147], "Multiple-choice": [148], "ground": [151], "truth": [152], "options": [153], "derived": [154], "annotation": [157], "enable": [158], "an": [159], "objective": [160], "efficient": [162], "assessment": [163], "model": [165], "performance,": [166], "eliminating": [167], "need": [169], "or": [172], "GPT": [173], "intervention": [174], "during": [175], "evaluation.": [176], "We": [177], "further": [178], "evaluate": [179], "performance": [181], "22": [183], "prominent": [184], "open-source": [185], "summarize": [188], "valuable": [189], "observations.": [190], "By": [191], "revealing": [192], "through": [198], "extensive": [199], "evaluations,": [200], "aim": [202], "provide": [206], "insights": [207], "will": [209], "mo-tivate": [210], "future": [211], "research": [212], "toward": [213], "goal": [215], "General": [217], "Artificial": [218], "Intelligence.": [219], "Dataset": [220], "code": [223], "are": [224], "available": [225], "at": [226], "https://github.com/AILab-CVC/SEED-Bench.": [227]}, "counts_by_year": [{"year": 2026, "cited_by_count": 15}, {"year": 2025, "cited_by_count": 65}, {"year": 2024, "cited_by_count": 23}], "updated_date": "2026-05-09T13:55:54.758798", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4400362569", "doi": "https://doi.org/10.1038/s41467-024-50043-3", "title": "Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4", "display_name": "Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4", "relevance_score": 1356.9785, "publication_year": 2024, "publication_date": "2024-07-05", "ids": {"openalex": "https://openalex.org/W4400362569", "doi": "https://doi.org/10.1038/s41467-024-50043-3", "pmid": "https://pubmed.ncbi.nlm.nih.gov/38969632"}, "language": "en", "primary_location": {"id": "doi:10.1038/s41467-024-50043-3", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-50043-3", "pdf_url": "https://www.nature.com/articles/s41467-024-50043-3.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://www.nature.com/articles/s41467-024-50043-3.pdf", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5104653068", "display_name": "Juexiao Zhou", "orcid": null}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Juexiao Zhou", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "DermAssure, LLC, New York, NY, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "DermAssure, LLC, New York, NY, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5110510755", "display_name": "Xiaonan He", "orcid": "https://orcid.org/0000-0002-6713-608X"}, "institutions": [{"id": "https://openalex.org/I183519381", "display_name": "Capital Medical University", "ror": "https://ror.org/013xs5b60", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183519381"]}, {"id": "https://openalex.org/I4210119028", "display_name": "Beijing Anzhen Hospital", "ror": "https://ror.org/02h2j1586", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210119028"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xiaonan He", "raw_affiliation_strings": ["Emergency Critical Care Center, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China. hxndoctor@126.com", "Emergency Critical Care Center, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Emergency Critical Care Center, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China. hxndoctor@126.com", "institution_ids": ["https://openalex.org/I4210119028"]}, {"raw_affiliation_string": "Emergency Critical Care Center, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China", "institution_ids": ["https://openalex.org/I4210119028", "https://openalex.org/I183519381"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5064077135", "display_name": "Liyuan Sun", "orcid": "https://orcid.org/0000-0003-2043-2911"}, "institutions": [{"id": "https://openalex.org/I183519381", "display_name": "Capital Medical University", "ror": "https://ror.org/013xs5b60", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183519381"]}, {"id": "https://openalex.org/I4210119028", "display_name": "Beijing Anzhen Hospital", "ror": "https://ror.org/02h2j1586", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210119028"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Liyuan Sun", "raw_affiliation_strings": ["Department of Dermatology, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Dermatology, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China", "institution_ids": ["https://openalex.org/I4210119028", "https://openalex.org/I183519381"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102522732", "display_name": "Jiannan Xu", "orcid": null}, "institutions": [{"id": "https://openalex.org/I183519381", "display_name": "Capital Medical University", "ror": "https://ror.org/013xs5b60", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183519381"]}, {"id": "https://openalex.org/I4210119028", "display_name": "Beijing Anzhen Hospital", "ror": "https://ror.org/02h2j1586", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210119028"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiannan Xu", "raw_affiliation_strings": ["Department of Dermatology, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Dermatology, Beijing AnZhen Hospital, Affiliated to Capital Medical University, Beijing, China", "institution_ids": ["https://openalex.org/I4210119028", "https://openalex.org/I183519381"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101568161", "display_name": "Xiuying Chen", "orcid": "https://orcid.org/0000-0001-7598-0363"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Xiuying Chen", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5104128667", "display_name": "Yuetan Chu", "orcid": "https://orcid.org/0000-0003-1729-831X"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Yuetan Chu", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0003-1729-831X", "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010191987", "display_name": "Longxi Zhou", "orcid": "https://orcid.org/0000-0003-0116-9361"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Longxi Zhou", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0003-0116-9361", "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5088826157", "display_name": "Xingyu Liao", "orcid": "https://orcid.org/0000-0002-0061-1317"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Xingyu Liao", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0002-0061-1317", "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100392781", "display_name": "Bin Zhang", "orcid": "https://orcid.org/0000-0001-7313-9300"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Bin Zhang", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5104645244", "display_name": "Shawn Afvari", "orcid": null}, "institutions": [{"id": "https://openalex.org/I1283280774", "display_name": "Brigham and Women's Hospital", "ror": "https://ror.org/04b6nzv94", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283280774", "https://openalex.org/I48633490"]}, {"id": "https://openalex.org/I136199984", "display_name": "Harvard University", "ror": "https://ror.org/03vek6s52", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I136199984"]}, {"id": "https://openalex.org/I181190671", "display_name": "New York Medical College", "ror": "https://ror.org/03dkvy735", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I181190671"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Shawn Afvari", "raw_affiliation_strings": ["Department of Dermatology, Brigham and Women's Hospital, Harvard University, Boston, MA, USA", "DermAssure, LLC, New York, NY, USA", "School of Medicine, New York Medical College, Valhalla, NY, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Dermatology, Brigham and Women's Hospital, Harvard University, Boston, MA, USA", "institution_ids": ["https://openalex.org/I1283280774", "https://openalex.org/I136199984"]}, {"raw_affiliation_string": "DermAssure, LLC, New York, NY, USA", "institution_ids": []}, {"raw_affiliation_string": "School of Medicine, New York Medical College, Valhalla, NY, USA", "institution_ids": ["https://openalex.org/I181190671"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100618900", "display_name": "Xin Gao", "orcid": "https://orcid.org/0000-0002-7108-3574"}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Xin Gao", "raw_affiliation_strings": ["Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia. xin.gao@kaust.edu.sa", "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia. xin.gao@kaust.edu.sa", "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0002-7108-3574", "affiliations": [{"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia. xin.gao@kaust.edu.sa", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia. xin.gao@kaust.edu.sa", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}]}], "institutions": [], "countries_distinct_count": 3, "institutions_distinct_count": 11, "corresponding_author_ids": ["https://openalex.org/A5110510755"], "corresponding_institution_ids": ["https://openalex.org/I183519381", "https://openalex.org/I4210119028"], "apc_list": {"value": 3920, "currency": "GBP", "value_usd": 4808}, "apc_paid": {"value": 3920, "currency": "GBP", "value_usd": 4808}, "fwci": 35.6891, "has_fulltext": true, "cited_by_count": 141, "citation_normalized_percentile": {"value": 0.99865, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "15", "issue": "1", "first_page": "5649", "last_page": "5649"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10392", "display_name": "Cutaneous Melanoma Detection and Management", "score": 0.9983000159263611, "subfield": {"id": "https://openalex.org/subfields/2730", "display_name": "Oncology"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T10392", "display_name": "Cutaneous Melanoma Detection and Management", "score": 0.9983000159263611, "subfield": {"id": "https://openalex.org/subfields/2730", "display_name": "Oncology"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11713", "display_name": "Genital Health and Disease", "score": 0.9817000031471252, "subfield": {"id": "https://openalex.org/subfields/2746", "display_name": "Surgery"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10862", "display_name": "AI in cancer detection", "score": 0.9735000133514404, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/upload", "display_name": "Upload", "score": 0.7439529895782471}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6851234436035156}, {"id": "https://openalex.org/keywords/dermatological-diseases", "display_name": "Dermatological diseases", "score": 0.49238479137420654}, {"id": "https://openalex.org/keywords/task", "display_name": "Task (project management)", "score": 0.4275003671646118}, {"id": "https://openalex.org/keywords/certification", "display_name": "Certification", "score": 0.4191363751888275}, {"id": "https://openalex.org/keywords/skin-lesion", "display_name": "Skin lesion", "score": 0.4112417995929718}, {"id": "https://openalex.org/keywords/medicine", "display_name": "Medicine", "score": 0.3686622679233551}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.36148515343666077}, {"id": "https://openalex.org/keywords/dermatology", "display_name": "Dermatology", "score": 0.26353150606155396}, {"id": "https://openalex.org/keywords/world-wide-web", "display_name": "World Wide Web", "score": 0.1602315902709961}], "concepts": [{"id": "https://openalex.org/C71901391", "wikidata": "https://www.wikidata.org/wiki/Q7126699", "display_name": "Upload", "level": 2, "score": 0.7439529895782471}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6851234436035156}, {"id": "https://openalex.org/C2909963953", "wikidata": "https://www.wikidata.org/wiki/Q171171", "display_name": "Dermatological diseases", "level": 2, "score": 0.49238479137420654}, {"id": "https://openalex.org/C2780451532", "wikidata": "https://www.wikidata.org/wiki/Q759676", "display_name": "Task (project management)", "level": 2, "score": 0.4275003671646118}, {"id": "https://openalex.org/C46304622", "wikidata": "https://www.wikidata.org/wiki/Q374814", "display_name": "Certification", "level": 2, "score": 0.4191363751888275}, {"id": "https://openalex.org/C2988168687", "wikidata": "https://www.wikidata.org/wiki/Q949302", "display_name": "Skin lesion", "level": 2, "score": 0.4112417995929718}, {"id": "https://openalex.org/C71924100", "wikidata": "https://www.wikidata.org/wiki/Q11190", "display_name": "Medicine", "level": 0, "score": 0.3686622679233551}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.36148515343666077}, {"id": "https://openalex.org/C16005928", "wikidata": "https://www.wikidata.org/wiki/Q171171", "display_name": "Dermatology", "level": 1, "score": 0.26353150606155396}, {"id": "https://openalex.org/C136764020", "wikidata": "https://www.wikidata.org/wiki/Q466", "display_name": "World Wide Web", "level": 1, "score": 0.1602315902709961}, {"id": "https://openalex.org/C187736073", "wikidata": "https://www.wikidata.org/wiki/Q2920921", "display_name": "Management", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C17744445", "wikidata": "https://www.wikidata.org/wiki/Q36442", "display_name": "Political science", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C199539241", "wikidata": "https://www.wikidata.org/wiki/Q7748", "display_name": "Law", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C162324750", "wikidata": "https://www.wikidata.org/wiki/Q8134", "display_name": "Economics", "level": 0, "score": 0.0}], "mesh": [{"descriptor_ui": "D000069550", "descriptor_name": "Machine Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000069550", "descriptor_name": "Machine Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000069550", "descriptor_name": "Machine Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D003198", "descriptor_name": "Computer Simulation", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D003198", "descriptor_name": "Computer Simulation", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D003198", "descriptor_name": "Computer Simulation", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D003880", "descriptor_name": "Dermatology", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D003880", "descriptor_name": "Dermatology", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D003880", "descriptor_name": "Dermatology", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D003880", "descriptor_name": "Dermatology", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D003880", "descriptor_name": "Dermatology", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D008954", "descriptor_name": "Models, Biological", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D008954", "descriptor_name": "Models, Biological", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D008954", "descriptor_name": "Models, Biological", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D012867", "descriptor_name": "Skin", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D012867", "descriptor_name": "Skin", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D012871", "descriptor_name": "Skin Diseases", "qualifier_ui": "Q000175", "qualifier_name": "diagnosis", "is_major_topic": true}, {"descriptor_ui": "D012871", "descriptor_name": "Skin Diseases", "qualifier_ui": "Q000175", "qualifier_name": "diagnosis", "is_major_topic": true}, {"descriptor_ui": "D012871", "descriptor_name": "Skin Diseases", "qualifier_ui": "Q000175", "qualifier_name": "diagnosis", "is_major_topic": true}, {"descriptor_ui": "D012871", "descriptor_name": "Skin Diseases", "qualifier_ui": "Q000175", "qualifier_name": "diagnosis", "is_major_topic": true}, {"descriptor_ui": "D012871", "descriptor_name": "Skin Diseases", "qualifier_ui": "Q000175", "qualifier_name": "diagnosis", "is_major_topic": true}, {"descriptor_ui": "D063731", "descriptor_name": "Mobile Applications", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D063731", "descriptor_name": "Mobile Applications", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D063731", "descriptor_name": "Mobile Applications", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}], "locations_count": 6, "locations": [{"id": "doi:10.1038/s41467-024-50043-3", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-50043-3", "pdf_url": "https://www.nature.com/articles/s41467-024-50043-3.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, {"id": "pmid:38969632", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/38969632", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature communications", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:11226626", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/11226626", "pdf_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11226626/pdf/41467_2024_Article_50043.pdf", "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Nat Commun", "raw_type": "Text"}, {"id": "pmh:oai:touroscholar.touro.edu:nymc_students_pubs-1300", "is_oa": false, "landing_page_url": "https://touroscholar.touro.edu/nymc_students_pubs/317", "pdf_url": null, "source": {"id": "https://openalex.org/S4377196437", "display_name": "Touro Scholar (Touro College)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I200437953", "host_organization_name": "Touro College", "host_organization_lineage": ["https://openalex.org/I200437953"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "NYMC Student Publications", "raw_type": "article"}, {"id": "pmh:oai:touroscholar.touro.edu:nymc_students_pubs-1394", "is_oa": false, "landing_page_url": "https://touroscholar.touro.edu/nymc_students_pubs/407", "pdf_url": null, "source": {"id": "https://openalex.org/S4377196437", "display_name": "Touro Scholar (Touro College)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I200437953", "host_organization_name": "Touro College", "host_organization_lineage": ["https://openalex.org/I200437953"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "NYMC Student Publications", "raw_type": "article"}, {"id": "pmh:oai:doaj.org/article:4cc0771c7c504516849eb9d83dc15cf9", "is_oa": false, "landing_page_url": "https://doaj.org/article/4cc0771c7c504516849eb9d83dc15cf9", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401280", "display_name": "DOAJ (DOAJ: Directory of Open Access Journals)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)", "raw_type": "article"}], "best_oa_location": {"id": "doi:10.1038/s41467-024-50043-3", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-50043-3", "pdf_url": "https://www.nature.com/articles/s41467-024-50043-3.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, "sustainable_development_goals": [], "awards": [{"id": "https://openalex.org/G1825332442", "display_name": null, "funder_award_id": "REI/1/5202-01-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}, {"id": "https://openalex.org/G4411873601", "display_name": null, "funder_award_id": "62272327", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G5141847693", "display_name": null, "funder_award_id": "REI/1/0018-01-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}, {"id": "https://openalex.org/G5289953175", "display_name": null, "funder_award_id": "REI/1/5234-01-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}, {"id": "https://openalex.org/G8253667702", "display_name": null, "funder_award_id": "FCC/1/1976-44-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}, {"id": "https://openalex.org/G8644074954", "display_name": null, "funder_award_id": "RGC/3/4816-01-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}, {"id": "https://openalex.org/G8848196204", "display_name": null, "funder_award_id": "REI/1/4940-01-01", "funder_id": "https://openalex.org/F4320322320", "funder_display_name": "King Abdullah University of Science and Technology"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}, {"id": "https://openalex.org/F4320322320", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38"}], "has_content": {"pdf": true, "grobid_xml": false}, "content_urls": {"pdf": "https://content.openalex.org/works/W4400362569.pdf"}, "referenced_works_count": 74, "referenced_works": ["https://openalex.org/W1932469787", "https://openalex.org/W2012945985", "https://openalex.org/W2051521434", "https://openalex.org/W2051772831", "https://openalex.org/W2061414922", "https://openalex.org/W2067225558", "https://openalex.org/W2072629969", "https://openalex.org/W2519210008", "https://openalex.org/W2581082771", "https://openalex.org/W2607363228", "https://openalex.org/W2742893201", "https://openalex.org/W2757940437", "https://openalex.org/W2765773998", "https://openalex.org/W2778753784", "https://openalex.org/W2784963878", "https://openalex.org/W2785200097", "https://openalex.org/W2786147899", "https://openalex.org/W2806853752", "https://openalex.org/W2807032201", "https://openalex.org/W2886641317", "https://openalex.org/W2892053105", "https://openalex.org/W2892342267", "https://openalex.org/W2903060508", "https://openalex.org/W2917303411", "https://openalex.org/W2941548848", "https://openalex.org/W2945626616", "https://openalex.org/W2947367580", "https://openalex.org/W2952971376", "https://openalex.org/W2963258365", "https://openalex.org/W2993820249", "https://openalex.org/W3014403957", "https://openalex.org/W3025011581", "https://openalex.org/W3025830737", "https://openalex.org/W3094502228", "https://openalex.org/W3105070630", "https://openalex.org/W3175183715", "https://openalex.org/W3177881847", "https://openalex.org/W3209532394", "https://openalex.org/W4205164650", "https://openalex.org/W4205499468", "https://openalex.org/W4206961607", "https://openalex.org/W4207031999", "https://openalex.org/W4212936931", "https://openalex.org/W4220786947", "https://openalex.org/W4255689753", "https://openalex.org/W4281783336", "https://openalex.org/W4284898303", "https://openalex.org/W4290852327", "https://openalex.org/W4292830232", "https://openalex.org/W4300035993", "https://openalex.org/W4319662928", "https://openalex.org/W4321459182", "https://openalex.org/W4322718191", "https://openalex.org/W4322766760", "https://openalex.org/W4323030608", "https://openalex.org/W4323348223", "https://openalex.org/W4323830259", "https://openalex.org/W4324387439", "https://openalex.org/W4360763710", "https://openalex.org/W4360836968", "https://openalex.org/W4361282369", "https://openalex.org/W4361289889", "https://openalex.org/W4364295707", "https://openalex.org/W4375830716", "https://openalex.org/W4376134609", "https://openalex.org/W4379259189", "https://openalex.org/W4383815588", "https://openalex.org/W4384071683", "https://openalex.org/W4386076522", "https://openalex.org/W4387409742", "https://openalex.org/W4389518968", "https://openalex.org/W4389977669", "https://openalex.org/W4391418271", "https://openalex.org/W6739901393"], "related_works": ["https://openalex.org/W2944823289", "https://openalex.org/W3037018281", "https://openalex.org/W2003209439", "https://openalex.org/W4321854979", "https://openalex.org/W2066052364", "https://openalex.org/W2358319515", "https://openalex.org/W2972592048", "https://openalex.org/W2023743128", "https://openalex.org/W4312214821", "https://openalex.org/W4285100856"], "abstract_inverted_index": {"Large": [0], "language": [1, 58], "models": [2], "(LLMs)": [3], "are": [4], "seen": [5], "to": [6, 36], "have": [7, 61, 102], "tremendous": [8], "potential": [9], "in": [10, 16], "advancing": [11], "medical": [12], "diagnosis": [13], "recently,": [14], "particularly": [15], "dermatological": [17], "diagnosis,": [18, 123], "which": [19, 47], "is": [20, 48], "a": [21, 63, 97], "very": [22], "important": [23], "task": [24], "as": [25], "skin": [26, 78, 120, 139], "and": [27, 85, 92, 95, 124, 135, 144], "subcutaneous": [28], "diseases": [29], "rank": [30], "high": [31], "among": [32], "the": [33, 37, 125, 130, 133, 138], "leading": [34], "contributors": [35], "global": [38], "burden": [39], "of": [40, 77, 137], "nonfatal": [41], "diseases.": [42], "Here": [43], "we": [44], "present": [45], "SkinGPT-4,": [46, 114], "an": [49, 68, 74], "interactive": [50, 146], "dermatology": [51], "diagnostic": [52], "system": [53, 126], "based": [54], "on": [55, 106], "multimodal": [56], "large": [57], "models.": [59], "We": [60, 101], "aligned": [62], "pre-trained": [64], "vision": [65], "transformer": [66], "with": [67, 89, 110], "LLM": [69], "named": [70], "Llama-2-13b-chat": [71], "by": [72], "collecting": [73], "extensive": [75], "collection": [76], "disease": [79], "images": [80], "(comprising": [81], "52,929": [82], "publicly": [83], "available": [84], "proprietary": [86], "images)": [87], "along": [88], "clinical": [90], "concepts": [91], "doctors'": [93], "notes,": [94], "designing": [96], "two-step": [98], "training": [99], "strategy.": [100], "quantitatively": [103], "evaluated": [104], "SkinGPT-4": [105], "150": [107], "real-life": [108], "cases": [109], "board-certified": [111], "dermatologists.": [112], "With": [113], "users": [115], "could": [116, 127], "upload": [117], "their": [118], "own": [119], "photos": [121], "for": [122], "autonomously": [128], "evaluate": [129], "images,": [131], "identify": [132], "characteristics": [134], "categories": [136], "conditions,": [140], "perform": [141], "in-depth": [142], "analysis,": [143], "provide": [145], "treatment": [147], "recommendations.": [148]}, "counts_by_year": [{"year": 2026, "cited_by_count": 37}, {"year": 2025, "cited_by_count": 95}, {"year": 2024, "cited_by_count": 9}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4401770219", "doi": "https://doi.org/10.1007/s11263-024-02214-4", "title": "Contextual Object Detection with Multimodal Large Language Models", "display_name": "Contextual Object Detection with Multimodal Large Language Models", "relevance_score": 1279.1877, "publication_year": 2024, "publication_date": "2024-08-20", "ids": {"openalex": "https://openalex.org/W4401770219", "doi": "https://doi.org/10.1007/s11263-024-02214-4"}, "language": "en", "primary_location": {"id": "doi:10.1007/s11263-024-02214-4", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s11263-024-02214-4", "pdf_url": null, "source": {"id": "https://openalex.org/S25538012", "display_name": "International Journal of Computer Vision", "issn_l": "0920-5691", "issn": ["0920-5691", "1573-1405"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319900", "host_organization_name": "Springer Science+Business Media", "host_organization_lineage": ["https://openalex.org/P4310319900", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Science+Business Media", "Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Computer Vision", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5005200501", "display_name": "Yuhang Zang", "orcid": "https://orcid.org/0000-0003-1110-5062"}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Yuhang Zang", "raw_affiliation_strings": ["S-Lab, Nanyang Technological University, Singapore, Singapore"], "raw_orcid": "https://orcid.org/0000-0003-1110-5062", "affiliations": [{"raw_affiliation_string": "S-Lab, Nanyang Technological University, Singapore, Singapore", "institution_ids": ["https://openalex.org/I172675005"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115591090", "display_name": "Wei Li", "orcid": "https://orcid.org/0000-0002-9791-9763"}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Wei Li", "raw_affiliation_strings": ["S-Lab, Nanyang Technological University, Singapore, Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "S-Lab, Nanyang Technological University, Singapore, Singapore", "institution_ids": ["https://openalex.org/I172675005"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101898844", "display_name": "Jun Han", "orcid": null}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Jun Han", "raw_affiliation_strings": ["S-Lab, Nanyang Technological University, Singapore, Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "S-Lab, Nanyang Technological University, Singapore, Singapore", "institution_ids": ["https://openalex.org/I172675005"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5030812622", "display_name": "Kaiyang Zhou", "orcid": "https://orcid.org/0000-0002-8153-3903"}, "institutions": [{"id": "https://openalex.org/I141568987", "display_name": "Hong Kong Baptist University", "ror": "https://ror.org/0145fw131", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I141568987"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Kaiyang Zhou", "raw_affiliation_strings": ["Hong Kong Baptist University, Kowloon Tong, Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Hong Kong Baptist University, Kowloon Tong, Hong Kong", "institution_ids": ["https://openalex.org/I141568987"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5005626854", "display_name": "Chen Change Loy", "orcid": "https://orcid.org/0000-0001-5345-1591"}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": true, "raw_author_name": "Chen Change Loy", "raw_affiliation_strings": ["S-Lab, Nanyang Technological University, Singapore, Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "S-Lab, Nanyang Technological University, Singapore, Singapore", "institution_ids": ["https://openalex.org/I172675005"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 5, "corresponding_author_ids": ["https://openalex.org/A5005626854"], "corresponding_institution_ids": ["https://openalex.org/I172675005"], "apc_list": {"value": 2890, "currency": "EUR", "value_usd": 3690}, "apc_paid": null, "fwci": 18.3075, "has_fulltext": false, "cited_by_count": 82, "citation_normalized_percentile": {"value": 0.99640275, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 90, "max": 100}, "biblio": {"volume": "133", "issue": "2", "first_page": "825", "last_page": "843"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9854000210762024, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10812", "display_name": "Human Pose and Action Recognition", "score": 0.9753999710083008, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.837561845779419}, {"id": "https://openalex.org/keywords/closed-captioning", "display_name": "Closed captioning", "score": 0.7184140682220459}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.6838256120681763}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.6010524034500122}, {"id": "https://openalex.org/keywords/object-detection", "display_name": "Object detection", "score": 0.5001211166381836}, {"id": "https://openalex.org/keywords/benchmark", "display_name": "Benchmark (surveying)", "score": 0.49735501408576965}, {"id": "https://openalex.org/keywords/object", "display_name": "Object (grammar)", "score": 0.48507848381996155}, {"id": "https://openalex.org/keywords/vocabulary", "display_name": "Vocabulary", "score": 0.47985929250717163}, {"id": "https://openalex.org/keywords/context", "display_name": "Context (archaeology)", "score": 0.46391645073890686}, {"id": "https://openalex.org/keywords/language-model", "display_name": "Language model", "score": 0.4449057877063751}, {"id": "https://openalex.org/keywords/encoder", "display_name": "Encoder", "score": 0.44176262617111206}, {"id": "https://openalex.org/keywords/minimum-bounding-box", "display_name": "Minimum bounding box", "score": 0.42559731006622314}, {"id": "https://openalex.org/keywords/segmentation", "display_name": "Segmentation", "score": 0.3371860682964325}, {"id": "https://openalex.org/keywords/image", "display_name": "Image (mathematics)", "score": 0.24618664383888245}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.10727187991142273}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.837561845779419}, {"id": "https://openalex.org/C157657479", "wikidata": "https://www.wikidata.org/wiki/Q2367247", "display_name": "Closed captioning", "level": 3, "score": 0.7184140682220459}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.6838256120681763}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.6010524034500122}, {"id": "https://openalex.org/C2776151529", "wikidata": "https://www.wikidata.org/wiki/Q3045304", "display_name": "Object detection", "level": 3, "score": 0.5001211166381836}, {"id": "https://openalex.org/C185798385", "wikidata": "https://www.wikidata.org/wiki/Q1161707", "display_name": "Benchmark (surveying)", "level": 2, "score": 0.49735501408576965}, {"id": "https://openalex.org/C2781238097", "wikidata": "https://www.wikidata.org/wiki/Q175026", "display_name": "Object (grammar)", "level": 2, "score": 0.48507848381996155}, {"id": "https://openalex.org/C2777601683", "wikidata": "https://www.wikidata.org/wiki/Q6499736", "display_name": "Vocabulary", "level": 2, "score": 0.47985929250717163}, {"id": "https://openalex.org/C2779343474", "wikidata": "https://www.wikidata.org/wiki/Q3109175", "display_name": "Context (archaeology)", "level": 2, "score": 0.46391645073890686}, {"id": "https://openalex.org/C137293760", "wikidata": "https://www.wikidata.org/wiki/Q3621696", "display_name": "Language model", "level": 2, "score": 0.4449057877063751}, {"id": "https://openalex.org/C118505674", "wikidata": "https://www.wikidata.org/wiki/Q42586063", "display_name": "Encoder", "level": 2, "score": 0.44176262617111206}, {"id": "https://openalex.org/C147037132", "wikidata": "https://www.wikidata.org/wiki/Q6865426", "display_name": "Minimum bounding box", "level": 3, "score": 0.42559731006622314}, {"id": "https://openalex.org/C89600930", "wikidata": "https://www.wikidata.org/wiki/Q1423946", "display_name": "Segmentation", "level": 2, "score": 0.3371860682964325}, {"id": "https://openalex.org/C115961682", "wikidata": "https://www.wikidata.org/wiki/Q860623", "display_name": "Image (mathematics)", "level": 2, "score": 0.24618664383888245}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.10727187991142273}, {"id": "https://openalex.org/C13280743", "wikidata": "https://www.wikidata.org/wiki/Q131089", "display_name": "Geodesy", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C86803240", "wikidata": "https://www.wikidata.org/wiki/Q420", "display_name": "Biology", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C111919701", "wikidata": "https://www.wikidata.org/wiki/Q9135", "display_name": "Operating system", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C205649164", "wikidata": "https://www.wikidata.org/wiki/Q1071", "display_name": "Geography", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C151730666", "wikidata": "https://www.wikidata.org/wiki/Q7205", "display_name": "Paleontology", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.0}], "mesh": [], "locations_count": 2, "locations": [{"id": "doi:10.1007/s11263-024-02214-4", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s11263-024-02214-4", "pdf_url": null, "source": {"id": "https://openalex.org/S25538012", "display_name": "International Journal of Computer Vision", "issn_l": "0920-5691", "issn": ["0920-5691", "1573-1405"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319900", "host_organization_name": "Springer Science+Business Media", "host_organization_lineage": ["https://openalex.org/P4310319900", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Science+Business Media", "Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Computer Vision", "raw_type": "journal-article"}, {"id": "pmh:oai:dr.ntu.edu.sg:10356/181063", "is_oa": false, "landing_page_url": "https://hdl.handle.net/10356/181063", "pdf_url": null, "source": {"id": "https://openalex.org/S4306402609", "display_name": "DR-NTU (Nanyang Technological University)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I172675005", "host_organization_name": "Nanyang Technological University", "host_organization_lineage": ["https://openalex.org/I172675005"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "Journal Article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.8100000023841858, "display_name": "Quality Education"}], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 70, "referenced_works": ["https://openalex.org/W1773149199", "https://openalex.org/W1861492603", "https://openalex.org/W1905882502", "https://openalex.org/W1933349210", "https://openalex.org/W2031489346", "https://openalex.org/W2064675550", "https://openalex.org/W2108598243", "https://openalex.org/W2125215748", "https://openalex.org/W2185175083", "https://openalex.org/W2194775991", "https://openalex.org/W2520951797", "https://openalex.org/W2550553598", "https://openalex.org/W2560730294", "https://openalex.org/W2613718673", "https://openalex.org/W2745461083", "https://openalex.org/W2895403383", "https://openalex.org/W2948672349", "https://openalex.org/W2962766617", "https://openalex.org/W2963150697", "https://openalex.org/W2963936013", "https://openalex.org/W2964284374", "https://openalex.org/W2981852735", "https://openalex.org/W2982770724", "https://openalex.org/W2983943451", "https://openalex.org/W3012573144", "https://openalex.org/W3092462694", "https://openalex.org/W3096609285", "https://openalex.org/W3126337491", "https://openalex.org/W3135367836", "https://openalex.org/W3138516171", "https://openalex.org/W3159619744", "https://openalex.org/W3171547673", "https://openalex.org/W3173859428", "https://openalex.org/W3176659256", "https://openalex.org/W3177174258", "https://openalex.org/W3199245537", "https://openalex.org/W3206072662", "https://openalex.org/W3216551675", "https://openalex.org/W4200631575", "https://openalex.org/W4212774754", "https://openalex.org/W4221146106", "https://openalex.org/W4225323055", "https://openalex.org/W4241200240", "https://openalex.org/W4282919422", "https://openalex.org/W4284961860", "https://openalex.org/W4288083516", "https://openalex.org/W4297899309", "https://openalex.org/W4310557340", "https://openalex.org/W4312424618", "https://openalex.org/W4312563428", "https://openalex.org/W4312605942", "https://openalex.org/W4312747482", "https://openalex.org/W4312956471", "https://openalex.org/W4321612728", "https://openalex.org/W4386075493", "https://openalex.org/W4386076029", "https://openalex.org/W4386076222", "https://openalex.org/W4386076396", "https://openalex.org/W4389519987", "https://openalex.org/W4390871915", "https://openalex.org/W4390874575", "https://openalex.org/W4402727764", "https://openalex.org/W4404612908", "https://openalex.org/W6600234944", "https://openalex.org/W6639102338", "https://openalex.org/W6723035356", "https://openalex.org/W6739901393", "https://openalex.org/W6757817989", "https://openalex.org/W6778883912", "https://openalex.org/W6785652829"], "related_works": ["https://openalex.org/W4327500857", "https://openalex.org/W2965994363", "https://openalex.org/W4311223090", "https://openalex.org/W1689909837", "https://openalex.org/W4205729548", "https://openalex.org/W4298525700", "https://openalex.org/W1895541646", "https://openalex.org/W2953362004", "https://openalex.org/W2952251705", "https://openalex.org/W2889698616"], "abstract_inverted_index": null, "counts_by_year": [{"year": 2026, "cited_by_count": 14}, {"year": 2025, "cited_by_count": 52}, {"year": 2024, "cited_by_count": 15}, {"year": 2023, "cited_by_count": 1}], "updated_date": "2026-05-20T08:49:12.498775", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4404584849", "doi": "https://doi.org/10.1038/s41467-024-51465-9", "title": "In-context learning enables multimodal large language models to classify cancer pathology images", "display_name": "In-context learning enables multimodal large language models to classify cancer pathology images", "relevance_score": 1136.0626, "publication_year": 2024, "publication_date": "2024-11-21", "ids": {"openalex": "https://openalex.org/W4404584849", "doi": "https://doi.org/10.1038/s41467-024-51465-9", "pmid": "https://pubmed.ncbi.nlm.nih.gov/39572531"}, "language": "en", "primary_location": {"id": "doi:10.1038/s41467-024-51465-9", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-51465-9", "pdf_url": "https://www.nature.com/articles/s41467-024-51465-9.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "datacite", "doaj", "pubmed"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://www.nature.com/articles/s41467-024-51465-9.pdf", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5048917650", "display_name": "Dyke Ferber", "orcid": "https://orcid.org/0009-0006-6195-9276"}, "institutions": [{"id": "https://openalex.org/I223822909", "display_name": "Heidelberg University", "ror": "https://ror.org/038t36y30", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I223822909"]}, {"id": "https://openalex.org/I2802164966", "display_name": "University Hospital Heidelberg", "ror": "https://ror.org/013czdx64", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I2802164966"]}, {"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}, {"id": "https://openalex.org/I4210111460", "display_name": "National Center for Tumor Diseases", "ror": "https://ror.org/01txwsw02", "country_code": "DE", "type": "funder", "lineage": ["https://openalex.org/I4210111460"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Dyke Ferber", "raw_affiliation_strings": ["Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany", "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany", "institution_ids": ["https://openalex.org/I2802164966", "https://openalex.org/I223822909"]}, {"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}, {"raw_affiliation_string": "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany", "institution_ids": ["https://openalex.org/I4210111460", "https://openalex.org/I223822909", "https://openalex.org/I2802164966"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5056031179", "display_name": "Georg W\u00f6lflein", "orcid": "https://orcid.org/0000-0002-0407-7617"}, "institutions": [{"id": "https://openalex.org/I16835326", "display_name": "University of St Andrews", "ror": "https://ror.org/02wn5qz54", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I16835326"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Georg W\u00f6lflein", "raw_affiliation_strings": ["School of Computer Science, University of St Andrews, St Andrews, UK"], "raw_orcid": "https://orcid.org/0000-0002-0407-7617", "affiliations": [{"raw_affiliation_string": "School of Computer Science, University of St Andrews, St Andrews, UK", "institution_ids": ["https://openalex.org/I16835326"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5020954920", "display_name": "Isabella C. Wiest", "orcid": "https://orcid.org/0009-0004-4848-614X"}, "institutions": [{"id": "https://openalex.org/I223822909", "display_name": "Heidelberg University", "ror": "https://ror.org/038t36y30", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I223822909"]}, {"id": "https://openalex.org/I2802164966", "display_name": "University Hospital Heidelberg", "ror": "https://ror.org/013czdx64", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I2802164966"]}, {"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}, {"id": "https://openalex.org/I4210156450", "display_name": "University Medical Centre Mannheim", "ror": "https://ror.org/05sxbyd35", "country_code": "DE", "type": "funder", "lineage": ["https://openalex.org/I4210156450"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Isabella C. Wiest", "raw_affiliation_strings": ["Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany", "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany", "institution_ids": ["https://openalex.org/I4210156450", "https://openalex.org/I223822909", "https://openalex.org/I2802164966"]}, {"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5056339832", "display_name": "Marta Ligero", "orcid": "https://orcid.org/0000-0001-9824-7316"}, "institutions": [{"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Marta Ligero", "raw_affiliation_strings": ["Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5036630887", "display_name": "Srividhya Sainath", "orcid": "https://orcid.org/0009-0006-6227-747X"}, "institutions": [{"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Srividhya Sainath", "raw_affiliation_strings": ["Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5057475480", "display_name": "Narmin Ghaffari Laleh", "orcid": "https://orcid.org/0000-0003-0889-3352"}, "institutions": [{"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Narmin Ghaffari Laleh", "raw_affiliation_strings": ["Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": "https://orcid.org/0000-0003-0889-3352", "affiliations": [{"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5074325740", "display_name": "Omar S. M. El Nahhas", "orcid": "https://orcid.org/0000-0002-2542-2117"}, "institutions": [{"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Omar S. M. El Nahhas", "raw_affiliation_strings": ["Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055585858", "display_name": "Gustav M\u00fcller\u2010Franzes", "orcid": "https://orcid.org/0000-0002-7413-2570"}, "institutions": [{"id": "https://openalex.org/I4210120689", "display_name": "Universit\u00e4tsklinikum Aachen", "ror": "https://ror.org/02gm5zw39", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I4210120689"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Gustav M\u00fcller-Franzes", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany", "institution_ids": ["https://openalex.org/I4210120689"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5006080186", "display_name": "Dirk J\u00e4ger", "orcid": null}, "institutions": [{"id": "https://openalex.org/I223822909", "display_name": "Heidelberg University", "ror": "https://ror.org/038t36y30", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I223822909"]}, {"id": "https://openalex.org/I2802164966", "display_name": "University Hospital Heidelberg", "ror": "https://ror.org/013czdx64", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I2802164966"]}, {"id": "https://openalex.org/I4210111460", "display_name": "National Center for Tumor Diseases", "ror": "https://ror.org/01txwsw02", "country_code": "DE", "type": "funder", "lineage": ["https://openalex.org/I4210111460"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Dirk J\u00e4ger", "raw_affiliation_strings": ["Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany", "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany", "institution_ids": ["https://openalex.org/I2802164966", "https://openalex.org/I223822909"]}, {"raw_affiliation_string": "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany", "institution_ids": ["https://openalex.org/I4210111460", "https://openalex.org/I223822909", "https://openalex.org/I2802164966"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016512818", "display_name": "Daniel Truhn", "orcid": "https://orcid.org/0000-0002-9605-0728"}, "institutions": [{"id": "https://openalex.org/I4210120689", "display_name": "Universit\u00e4tsklinikum Aachen", "ror": "https://ror.org/02gm5zw39", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I4210120689"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Daniel Truhn", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany", "institution_ids": ["https://openalex.org/I4210120689"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5073483894", "display_name": "Jakob Nikolas Kather", "orcid": "https://orcid.org/0000-0002-3730-5348"}, "institutions": [{"id": "https://openalex.org/I223822909", "display_name": "Heidelberg University", "ror": "https://ror.org/038t36y30", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I223822909"]}, {"id": "https://openalex.org/I2802164966", "display_name": "University Hospital Heidelberg", "ror": "https://ror.org/013czdx64", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I2802164966"]}, {"id": "https://openalex.org/I4210108778", "display_name": "Fresenius (Germany)", "ror": "https://ror.org/01v376g59", "country_code": "DE", "type": "company", "lineage": ["https://openalex.org/I4210108778"]}, {"id": "https://openalex.org/I4210111460", "display_name": "National Center for Tumor Diseases", "ror": "https://ror.org/01txwsw02", "country_code": "DE", "type": "funder", "lineage": ["https://openalex.org/I4210111460"]}, {"id": "https://openalex.org/I78650965", "display_name": "Technische Universit\u00e4t Dresden", "ror": "https://ror.org/042aqky30", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I78650965"]}], "countries": ["DE"], "is_corresponding": true, "raw_author_name": "Jakob Nikolas Kather", "raw_affiliation_strings": ["Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany. jakob_nikolas.kather@tu-dresden.de", "Department of Medicine I, University Hospital Dresden, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de", "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de", "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. jakob_nikolas.kather@tu-dresden.de", "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany"], "raw_orcid": "https://orcid.org/0000-0002-3730-5348", "affiliations": [{"raw_affiliation_string": "Department of Medical Oncology, Heidelberg University Hospital, Heidelberg, Germany. jakob_nikolas.kather@tu-dresden.de", "institution_ids": ["https://openalex.org/I223822909", "https://openalex.org/I2802164966"]}, {"raw_affiliation_string": "Department of Medicine I, University Hospital Dresden, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de", "institution_ids": ["https://openalex.org/I78650965"]}, {"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de", "institution_ids": ["https://openalex.org/I78650965"]}, {"raw_affiliation_string": "National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. jakob_nikolas.kather@tu-dresden.de", "institution_ids": ["https://openalex.org/I4210111460", "https://openalex.org/I223822909", "https://openalex.org/I2802164966"]}, {"raw_affiliation_string": "Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany", "institution_ids": ["https://openalex.org/I4210108778"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 11, "corresponding_author_ids": ["https://openalex.org/A5073483894"], "corresponding_institution_ids": ["https://openalex.org/I223822909", "https://openalex.org/I2802164966", "https://openalex.org/I4210108778", "https://openalex.org/I4210111460", "https://openalex.org/I78650965"], "apc_list": {"value": 3920, "currency": "GBP", "value_usd": 4808}, "apc_paid": {"value": 3920, "currency": "GBP", "value_usd": 4808}, "fwci": 37.9228, "has_fulltext": true, "cited_by_count": 120, "citation_normalized_percentile": {"value": 0.99852723, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 98, "max": 100}, "biblio": {"volume": "15", "issue": "1", "first_page": "10104", "last_page": "10104"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10862", "display_name": "AI in cancer detection", "score": 0.9991000294685364, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10862", "display_name": "AI in cancer detection", "score": 0.9991000294685364, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12422", "display_name": "Radiomics and Machine Learning in Medical Imaging", "score": 0.9927999973297119, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10552", "display_name": "Colorectal Cancer Screening and Detection", "score": 0.9854000210762024, "subfield": {"id": "https://openalex.org/subfields/2730", "display_name": "Oncology"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.8178532123565674}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.7262721061706543}, {"id": "https://openalex.org/keywords/machine-learning", "display_name": "Machine learning", "score": 0.5963438153266907}, {"id": "https://openalex.org/keywords/deep-learning", "display_name": "Deep learning", "score": 0.5706900358200073}, {"id": "https://openalex.org/keywords/subtyping", "display_name": "Subtyping", "score": 0.5507680773735046}, {"id": "https://openalex.org/keywords/context", "display_name": "Context (archaeology)", "score": 0.5344805717468262}, {"id": "https://openalex.org/keywords/image-processing", "display_name": "Image processing", "score": 0.41262608766555786}, {"id": "https://openalex.org/keywords/image", "display_name": "Image (mathematics)", "score": 0.17421084642410278}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.8178532123565674}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.7262721061706543}, {"id": "https://openalex.org/C119857082", "wikidata": "https://www.wikidata.org/wiki/Q2539", "display_name": "Machine learning", "level": 1, "score": 0.5963438153266907}, {"id": "https://openalex.org/C108583219", "wikidata": "https://www.wikidata.org/wiki/Q197536", "display_name": "Deep learning", "level": 2, "score": 0.5706900358200073}, {"id": "https://openalex.org/C83852419", "wikidata": "https://www.wikidata.org/wiki/Q2713292", "display_name": "Subtyping", "level": 2, "score": 0.5507680773735046}, {"id": "https://openalex.org/C2779343474", "wikidata": "https://www.wikidata.org/wiki/Q3109175", "display_name": "Context (archaeology)", "level": 2, "score": 0.5344805717468262}, {"id": "https://openalex.org/C9417928", "wikidata": "https://www.wikidata.org/wiki/Q1070689", "display_name": "Image processing", "level": 3, "score": 0.41262608766555786}, {"id": "https://openalex.org/C115961682", "wikidata": "https://www.wikidata.org/wiki/Q860623", "display_name": "Image (mathematics)", "level": 2, "score": 0.17421084642410278}, {"id": "https://openalex.org/C151730666", "wikidata": "https://www.wikidata.org/wiki/Q7205", "display_name": "Paleontology", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C86803240", "wikidata": "https://www.wikidata.org/wiki/Q420", "display_name": "Biology", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C199360897", "wikidata": "https://www.wikidata.org/wiki/Q9143", "display_name": "Programming language", "level": 1, "score": 0.0}], "mesh": [{"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000077321", "descriptor_name": "Deep Learning", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D000465", "descriptor_name": "Algorithms", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D001943", "descriptor_name": "Breast Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D003111", "descriptor_name": "Colonic Polyps", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D005260", "descriptor_name": "Female", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D006801", "descriptor_name": "Humans", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D007091", "descriptor_name": "Image Processing, Computer-Assisted", "qualifier_ui": "Q000379", "qualifier_name": "methods", "is_major_topic": true}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D009369", "descriptor_name": "Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": false}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000000981", "qualifier_name": "diagnostic imaging", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D015179", "descriptor_name": "Colorectal Neoplasms", "qualifier_ui": "Q000473", "qualifier_name": "pathology", "is_major_topic": true}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D016571", "descriptor_name": "Neural Networks, Computer", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}], "locations_count": 5, "locations": [{"id": "doi:10.1038/s41467-024-51465-9", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-51465-9", "pdf_url": "https://www.nature.com/articles/s41467-024-51465-9.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, {"id": "pmid:39572531", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/39572531", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature communications", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:11582649", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/11582649", "pdf_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11582649/pdf/41467_2024_Article_51465.pdf", "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Nat Commun", "raw_type": "Text"}, {"id": "pmh:oai:doaj.org/article:3fa7eb85942f4c83b6c9d066cad3cbe7", "is_oa": true, "landing_page_url": "https://doaj.org/article/3fa7eb85942f4c83b6c9d066cad3cbe7", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401280", "display_name": "DOAJ (DOAJ: Directory of Open Access Journals)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-sa", "license_id": "https://openalex.org/licenses/cc-by-sa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)", "raw_type": "article"}, {"id": "doi:10.18154/rwth-conv-254496", "is_oa": true, "landing_page_url": "https://doi.org/10.18154/rwth-conv-254496", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401033", "display_name": "RWTH Publications (RWTH Aachen)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I887968799", "host_organization_name": "RWTH Aachen University", "host_organization_lineage": ["https://openalex.org/I887968799"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": null, "is_accepted": false, "is_published": null, "raw_source_name": null, "raw_type": "article-journal"}], "best_oa_location": {"id": "doi:10.1038/s41467-024-51465-9", "is_oa": true, "landing_page_url": "https://doi.org/10.1038/s41467-024-51465-9", "pdf_url": "https://www.nature.com/articles/s41467-024-51465-9.pdf", "source": {"id": "https://openalex.org/S64187185", "display_name": "Nature Communications", "issn_l": "2041-1723", "issn": ["2041-1723"], "is_oa": true, "is_in_doaj": true, "is_core": true, "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Communications", "raw_type": "journal-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.5799999833106995, "display_name": "Quality Education"}], "awards": [{"id": "https://openalex.org/G1569319872", "display_name": null, "funder_award_id": "ZMVI1-2520DAT111", "funder_id": "https://openalex.org/F4320321721", "funder_display_name": "Bundesministerium f\u00fcr Gesundheit"}, {"id": "https://openalex.org/G1966681460", "display_name": null, "funder_award_id": "01KD2215A", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G2341156914", "display_name": null, "funder_award_id": "01EO2101", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G2654538971", "display_name": null, "funder_award_id": "101057091", "funder_id": "https://openalex.org/F4320334322", "funder_display_name": "HORIZON EUROPE Framework Programme"}, {"id": "https://openalex.org/G2669879858", "display_name": null, "funder_award_id": "01VSF21048", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G2820917408", "display_name": null, "funder_award_id": "01VSF21048", "funder_id": "https://openalex.org/F4320328691", "funder_display_name": "Gemeinsame Bundesausschuss"}, {"id": "https://openalex.org/G2888424188", "display_name": null, "funder_award_id": "2520DAT111", "funder_id": "https://openalex.org/F4320321721", "funder_display_name": "Bundesministerium f\u00fcr Gesundheit"}, {"id": "https://openalex.org/G3512296018", "display_name": null, "funder_award_id": "101096312", "funder_id": "https://openalex.org/F4320320300", "funder_display_name": "European Commission"}, {"id": "https://openalex.org/G3717981967", "display_name": null, "funder_award_id": "NIHR213331", "funder_id": "https://openalex.org/F4320319990", "funder_display_name": "National Institute for Health and Care Research"}, {"id": "https://openalex.org/G451588841", "display_name": null, "funder_award_id": "101057091", "funder_id": "https://openalex.org/F4320320300", "funder_display_name": "European Commission"}, {"id": "https://openalex.org/G4712284355", "display_name": null, "funder_award_id": "57616814", "funder_id": "https://openalex.org/F4320320875", "funder_display_name": "Deutscher Akademischer Austauschdienst"}, {"id": "https://openalex.org/G6098565189", "display_name": null, "funder_award_id": "57616814", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G8004974288", "display_name": null, "funder_award_id": "70113864", "funder_id": "https://openalex.org/F4320323556", "funder_display_name": "Deutsche Krebshilfe"}, {"id": "https://openalex.org/G8223481575", "display_name": null, "funder_award_id": "01KD2215B", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G826797920", "display_name": null, "funder_award_id": "01KD2104C", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G8311021456", "display_name": null, "funder_award_id": "031L0312A", "funder_id": "https://openalex.org/F4320321114", "funder_display_name": "Bundesministerium f\u00fcr Bildung und Forschung"}, {"id": "https://openalex.org/G8808717806", "display_name": null, "funder_award_id": "2520DAT111", "funder_id": "https://openalex.org/F4320323556", "funder_display_name": "Deutsche Krebshilfe"}], "funders": [{"id": "https://openalex.org/F4320319990", "display_name": "National Institute for Health and Care Research", "ror": "https://ror.org/0187kwz08"}, {"id": "https://openalex.org/F4320319994", "display_name": "Department of Health and Social Care", "ror": "https://ror.org/03sbpja79"}, {"id": "https://openalex.org/F4320320300", "display_name": "European Commission", "ror": "https://ror.org/00k4n6c32"}, {"id": "https://openalex.org/F4320320875", "display_name": "Deutscher Akademischer Austauschdienst", "ror": "https://ror.org/039djdh30"}, {"id": "https://openalex.org/F4320321114", "display_name": "Bundesministerium f\u00fcr Bildung und Forschung", "ror": "https://ror.org/04pz7b180"}, {"id": "https://openalex.org/F4320321721", "display_name": "Bundesministerium f\u00fcr Gesundheit", "ror": "https://ror.org/05vp4ka74"}, {"id": "https://openalex.org/F4320323556", "display_name": "Deutsche Krebshilfe", "ror": "https://ror.org/01wxdd722"}, {"id": "https://openalex.org/F4320328691", "display_name": "Gemeinsame Bundesausschuss", "ror": "https://ror.org/008c2qm47"}, {"id": "https://openalex.org/F4320334322", "display_name": "HORIZON EUROPE Framework Programme", "ror": null}], "has_content": {"pdf": true, "grobid_xml": true}, "content_urls": {"pdf": "https://content.openalex.org/works/W4404584849.pdf", "grobid_xml": "https://content.openalex.org/works/W4404584849.grobid-xml"}, "referenced_works_count": 24, "referenced_works": ["https://openalex.org/W2071216463", "https://openalex.org/W2581082771", "https://openalex.org/W2616247523", "https://openalex.org/W2760946358", "https://openalex.org/W2772723798", "https://openalex.org/W2914568698", "https://openalex.org/W2948930564", "https://openalex.org/W2956228567", "https://openalex.org/W3102564565", "https://openalex.org/W3129831491", "https://openalex.org/W3135547872", "https://openalex.org/W3173898803", "https://openalex.org/W3203168750", "https://openalex.org/W4293476620", "https://openalex.org/W4296693015", "https://openalex.org/W4324308124", "https://openalex.org/W4382678522", "https://openalex.org/W4385285835", "https://openalex.org/W4385948838", "https://openalex.org/W4386303022", "https://openalex.org/W4386697749", "https://openalex.org/W4387744047", "https://openalex.org/W4402581324", "https://openalex.org/W6601141708"], "related_works": ["https://openalex.org/W2396009657", "https://openalex.org/W2799110842", "https://openalex.org/W3032826521", "https://openalex.org/W2391332606", "https://openalex.org/W4229853287", "https://openalex.org/W1462775415", "https://openalex.org/W2008549446", "https://openalex.org/W1535483699", "https://openalex.org/W4399363637", "https://openalex.org/W4380075502"], "abstract_inverted_index": {"Medical": [0], "image": [1, 57, 75], "classification": [2], "requires": [3], "labeled,": [4], "task-specific": [5], "datasets": [6], "which": [7], "are": [8], "used": [9], "to": [10, 18, 114, 154, 168], "train": [11], "deep": [12], "learning": [13, 34, 52, 79, 111], "networks": [14, 121], "de": [15], "novo,": [16], "or": [17, 116], "fine-tune": [19], "foundation": [20], "models.": [21], "However,": [22], "this": [23, 136], "process": [24], "is": [25, 112, 180], "computationally": [26], "and": [27, 98], "technically": [28], "demanding.": [29], "In": [30, 134], "language": [31, 142], "processing,": [32], "in-context": [33, 51, 78, 110], "provides": [35], "an": [36], "alternative,": [37], "where": [38, 177], "models": [39, 143, 167], "learn": [40], "from": [41], "within": [42], "prompts,": [43], "bypassing": [44], "the": [45, 63], "need": [46], "for": [47, 123, 175], "parameter": [48], "updates.": [49], "Yet,": [50], "remains": [53], "underexplored": [54], "in": [55, 92, 102, 159], "medical": [56, 156, 169], "analysis.": [58], "Here,": [59], "we": [60], "systematically": [61], "evaluate": [62], "model": [64], "Generative": [65], "Pretrained": [66], "Transformer": [67], "4": [68], "with": [69, 77], "Vision": [70], "capabilities": [71], "(GPT-4V)": [72], "on": [73, 80, 145], "cancer": [74, 82], "processing": [76], "three": [81], "histopathology": [83], "tasks": [84, 158], "of": [85, 89, 132, 164], "high": [86], "importance:": [87], "Classification": [88], "tissue": [90], "subtypes": [91], "colorectal": [93], "cancer,": [94], "colon": [95], "polyp": [96], "subtyping": [97], "breast": [99], "tumor": [100], "detection": [101], "lymph": [103], "node": [104], "sections.": [105], "Our": [106], "results": [107], "show": [108], "that": [109, 139], "sufficient": [113], "match": [115], "even": [117], "outperform": [118], "specialized": [119], "neural": [120], "trained": [122, 144], "particular": [124], "tasks,": [125], "while": [126], "only": [127], "requiring": [128], "a": [129], "minimal": [130], "number": [131], "samples.": [133], "summary,": [135], "study": [137], "demonstrates": [138], "large": [140], "vision": [141], "non-domain": [146], "specific": [147], "data": [148, 179], "can": [149], "be": [150], "applied": [151], "out-of-the": [152], "box": [153], "solve": [155], "image-processing": [157], "histopathology.": [160], "This": [161], "democratizes": [162], "access": [163], "generalist": [165], "AI": [166], "experts": [170], "without": [171], "technical": [172], "background": [173], "especially": [174], "areas": [176], "annotated": [178], "scarce.": [181]}, "counts_by_year": [{"year": 2026, "cited_by_count": 32}, {"year": 2025, "cited_by_count": 83}, {"year": 2024, "cited_by_count": 5}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2024-11-22T00:00:00"}, {"id": "https://openalex.org/W4399399400", "doi": "https://doi.org/10.1109/tgrs.2024.3409624", "title": "EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain", "display_name": "EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain", "relevance_score": 1127.1226, "publication_year": 2024, "publication_date": "2024-01-01", "ids": {"openalex": "https://openalex.org/W4399399400", "doi": "https://doi.org/10.1109/tgrs.2024.3409624"}, "language": "en", "primary_location": {"id": "doi:10.1109/tgrs.2024.3409624", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tgrs.2024.3409624", "pdf_url": null, "source": {"id": "https://openalex.org/S111326731", "display_name": "IEEE Transactions on Geoscience and Remote Sensing", "issn_l": "0196-2892", "issn": ["0196-2892", "1558-0644"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319808", "host_organization_name": "Institute of Electrical and Electronics Engineers", "host_organization_lineage": ["https://openalex.org/P4310319808"], "host_organization_lineage_names": ["Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Transactions on Geoscience and Remote Sensing", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5092401779", "display_name": "Wei Zhang", "orcid": "https://orcid.org/0009-0003-7332-126X"}, "institutions": [{"id": "https://openalex.org/I125839683", "display_name": "Beijing Institute of Technology", "ror": "https://ror.org/01skt4w74", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I125839683", "https://openalex.org/I890469752"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Wei Zhang", "raw_affiliation_strings": ["Advanced Research Institute of Multidisciplinary Sciences and the School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"], "raw_orcid": "https://orcid.org/0009-0003-7332-126X", "affiliations": [{"raw_affiliation_string": "Advanced Research Institute of Multidisciplinary Sciences and the School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}, {"raw_affiliation_string": "School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102999194", "display_name": "Miaoxin Cai", "orcid": "https://orcid.org/0009-0007-2584-5949"}, "institutions": [{"id": "https://openalex.org/I125839683", "display_name": "Beijing Institute of Technology", "ror": "https://ror.org/01skt4w74", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I125839683", "https://openalex.org/I890469752"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Miaoxin Cai", "raw_affiliation_strings": ["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"], "raw_orcid": "https://orcid.org/0009-0007-2584-5949", "affiliations": [{"raw_affiliation_string": "National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100688517", "display_name": "Tong Zhang", "orcid": "https://orcid.org/0000-0002-1769-9829"}, "institutions": [{"id": "https://openalex.org/I125839683", "display_name": "Beijing Institute of Technology", "ror": "https://ror.org/01skt4w74", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I125839683", "https://openalex.org/I890469752"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tong Zhang", "raw_affiliation_strings": ["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0002-1769-9829", "affiliations": [{"raw_affiliation_string": "National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5023179941", "display_name": "Yin Zhuang", "orcid": "https://orcid.org/0000-0002-0443-1081"}, "institutions": [{"id": "https://openalex.org/I125839683", "display_name": "Beijing Institute of Technology", "ror": "https://ror.org/01skt4w74", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I125839683", "https://openalex.org/I890469752"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yin Zhuang", "raw_affiliation_strings": ["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5001776125", "display_name": "Xuerui Mao", "orcid": "https://orcid.org/0000-0002-8452-5773"}, "institutions": [{"id": "https://openalex.org/I125839683", "display_name": "Beijing Institute of Technology", "ror": "https://ror.org/01skt4w74", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I125839683", "https://openalex.org/I890469752"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xuerui Mao", "raw_affiliation_strings": ["Advanced Research Institute of Multidisciplinary Sciences and the School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Advanced Research Institute of Multidisciplinary Sciences and the School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}, {"raw_affiliation_string": "School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China", "institution_ids": ["https://openalex.org/I125839683"]}, {"raw_affiliation_string": "Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China", "institution_ids": ["https://openalex.org/I125839683"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 5, "corresponding_author_ids": ["https://openalex.org/A5092401779"], "corresponding_institution_ids": ["https://openalex.org/I125839683"], "apc_list": null, "apc_paid": null, "fwci": 29.6084, "has_fulltext": false, "cited_by_count": 131, "citation_normalized_percentile": {"value": 0.99848793, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "62", "issue": null, "first_page": "1", "last_page": "20"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10824", "display_name": "Image Retrieval and Classification Techniques", "score": 0.9377999901771545, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10824", "display_name": "Image Retrieval and Classification Techniques", "score": 0.9377999901771545, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10689", "display_name": "Remote-Sensing Image Classification", "score": 0.9235000014305115, "subfield": {"id": "https://openalex.org/subfields/2214", "display_name": "Media Technology"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10757", "display_name": "Geographic Information Systems Studies", "score": 0.9178000092506409, "subfield": {"id": "https://openalex.org/subfields/3305", "display_name": "Geography, Planning and Development"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6847436428070068}, {"id": "https://openalex.org/keywords/modal", "display_name": "Modal", "score": 0.650966227054596}, {"id": "https://openalex.org/keywords/remote-sensing", "display_name": "Remote sensing", "score": 0.5968299508094788}, {"id": "https://openalex.org/keywords/image-sensor", "display_name": "Image sensor", "score": 0.47007328271865845}, {"id": "https://openalex.org/keywords/domain", "display_name": "Domain (mathematical analysis)", "score": 0.46850067377090454}, {"id": "https://openalex.org/keywords/image", "display_name": "Image (mathematics)", "score": 0.4338591992855072}, {"id": "https://openalex.org/keywords/comprehension", "display_name": "Comprehension", "score": 0.4240010976791382}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.3888704776763916}, {"id": "https://openalex.org/keywords/computer-vision", "display_name": "Computer vision", "score": 0.33792755007743835}, {"id": "https://openalex.org/keywords/geology", "display_name": "Geology", "score": 0.14133325219154358}, {"id": "https://openalex.org/keywords/mathematics", "display_name": "Mathematics", "score": 0.0942126214504242}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6847436428070068}, {"id": "https://openalex.org/C71139939", "wikidata": "https://www.wikidata.org/wiki/Q910194", "display_name": "Modal", "level": 2, "score": 0.650966227054596}, {"id": "https://openalex.org/C62649853", "wikidata": "https://www.wikidata.org/wiki/Q199687", "display_name": "Remote sensing", "level": 1, "score": 0.5968299508094788}, {"id": "https://openalex.org/C76935873", "wikidata": "https://www.wikidata.org/wiki/Q209121", "display_name": "Image sensor", "level": 2, "score": 0.47007328271865845}, {"id": "https://openalex.org/C36503486", "wikidata": "https://www.wikidata.org/wiki/Q11235244", "display_name": "Domain (mathematical analysis)", "level": 2, "score": 0.46850067377090454}, {"id": "https://openalex.org/C115961682", "wikidata": "https://www.wikidata.org/wiki/Q860623", "display_name": "Image (mathematics)", "level": 2, "score": 0.4338591992855072}, {"id": "https://openalex.org/C511192102", "wikidata": "https://www.wikidata.org/wiki/Q5156948", "display_name": "Comprehension", "level": 2, "score": 0.4240010976791382}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.3888704776763916}, {"id": "https://openalex.org/C31972630", "wikidata": "https://www.wikidata.org/wiki/Q844240", "display_name": "Computer vision", "level": 1, "score": 0.33792755007743835}, {"id": "https://openalex.org/C127313418", "wikidata": "https://www.wikidata.org/wiki/Q1069", "display_name": "Geology", "level": 0, "score": 0.14133325219154358}, {"id": "https://openalex.org/C33923547", "wikidata": "https://www.wikidata.org/wiki/Q395", "display_name": "Mathematics", "level": 0, "score": 0.0942126214504242}, {"id": "https://openalex.org/C185592680", "wikidata": "https://www.wikidata.org/wiki/Q2329", "display_name": "Chemistry", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C199360897", "wikidata": "https://www.wikidata.org/wiki/Q9143", "display_name": "Programming language", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C188027245", "wikidata": "https://www.wikidata.org/wiki/Q750446", "display_name": "Polymer chemistry", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C134306372", "wikidata": "https://www.wikidata.org/wiki/Q7754", "display_name": "Mathematical analysis", "level": 1, "score": 0.0}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/tgrs.2024.3409624", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tgrs.2024.3409624", "pdf_url": null, "source": {"id": "https://openalex.org/S111326731", "display_name": "IEEE Transactions on Geoscience and Remote Sensing", "issn_l": "0196-2892", "issn": ["0196-2892", "1558-0644"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319808", "host_organization_name": "Institute of Electrical and Electronics Engineers", "host_organization_lineage": ["https://openalex.org/P4310319808"], "host_organization_lineage_names": ["Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Transactions on Geoscience and Remote Sensing", "raw_type": "journal-article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.800000011920929, "display_name": "Quality Education"}], "awards": [{"id": "https://openalex.org/G4914362321", "display_name": null, "funder_award_id": "92152109", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}, {"id": "https://openalex.org/G6434704085", "display_name": null, "funder_award_id": "62371048", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 131, "referenced_works": ["https://openalex.org/W1522301498", "https://openalex.org/W1614298861", "https://openalex.org/W1889081078", "https://openalex.org/W1958291604", "https://openalex.org/W1980038761", "https://openalex.org/W2020912318", "https://openalex.org/W2085625911", "https://openalex.org/W2296151615", "https://openalex.org/W2442626797", "https://openalex.org/W2510520237", "https://openalex.org/W2515866431", "https://openalex.org/W2577537809", "https://openalex.org/W2592962403", "https://openalex.org/W2764034829", "https://openalex.org/W2779054585", "https://openalex.org/W2779335303", "https://openalex.org/W2782522152", "https://openalex.org/W2911584214", "https://openalex.org/W2920981979", "https://openalex.org/W2935079508", "https://openalex.org/W2940726923", "https://openalex.org/W2947312908", "https://openalex.org/W2963250244", "https://openalex.org/W2964194231", "https://openalex.org/W2979382172", "https://openalex.org/W2986803748", "https://openalex.org/W2987734933", "https://openalex.org/W2997464028", "https://openalex.org/W3006792692", "https://openalex.org/W3012111773", "https://openalex.org/W3038948729", "https://openalex.org/W3041133507", "https://openalex.org/W3098351727", "https://openalex.org/W3100245404", "https://openalex.org/W3105577662", "https://openalex.org/W3110435696", "https://openalex.org/W3133008479", "https://openalex.org/W3134231019", "https://openalex.org/W3136761610", "https://openalex.org/W3144483443", "https://openalex.org/W3165084071", "https://openalex.org/W3168972675", "https://openalex.org/W3172075653", "https://openalex.org/W3173658130", "https://openalex.org/W3174004334", "https://openalex.org/W3174873843", "https://openalex.org/W3175205795", "https://openalex.org/W3200733355", "https://openalex.org/W3201797941", "https://openalex.org/W3202187941", "https://openalex.org/W3205100603", "https://openalex.org/W3209532394", "https://openalex.org/W4214490042", "https://openalex.org/W4214648418", "https://openalex.org/W4226456028", "https://openalex.org/W4283800076", "https://openalex.org/W4285505614", "https://openalex.org/W4292968451", "https://openalex.org/W4293649366", "https://openalex.org/W4308703323", "https://openalex.org/W4312605942", "https://openalex.org/W4312804579", "https://openalex.org/W4313145013", "https://openalex.org/W4318718936", "https://openalex.org/W4322707256", "https://openalex.org/W4322718191", "https://openalex.org/W4322718246", "https://openalex.org/W4324128075", "https://openalex.org/W4361229539", "https://openalex.org/W4362707064", "https://openalex.org/W4366208220", "https://openalex.org/W4366330503", "https://openalex.org/W4366598917", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4367628410", "https://openalex.org/W4376312115", "https://openalex.org/W4380994269", "https://openalex.org/W4384521492", "https://openalex.org/W4384918448", "https://openalex.org/W4385262477", "https://openalex.org/W4385436442", "https://openalex.org/W4386185600", "https://openalex.org/W4386384929", "https://openalex.org/W4386472879", "https://openalex.org/W4386794522", "https://openalex.org/W4387723654", "https://openalex.org/W4388685775", "https://openalex.org/W4389116425", "https://openalex.org/W4389261446", "https://openalex.org/W4389421438", "https://openalex.org/W4390137170", "https://openalex.org/W4390632550", "https://openalex.org/W4391212790", "https://openalex.org/W4391331851", "https://openalex.org/W4394938913", "https://openalex.org/W6631190155", "https://openalex.org/W6636510571", "https://openalex.org/W6639432524", "https://openalex.org/W6730365400", "https://openalex.org/W6763251565", "https://openalex.org/W6799579066", "https://openalex.org/W6802987763", "https://openalex.org/W6810334672", "https://openalex.org/W6849177959", "https://openalex.org/W6850015000", "https://openalex.org/W6850625674", "https://openalex.org/W6850787431", "https://openalex.org/W6851592950", "https://openalex.org/W6851800889", "https://openalex.org/W6851948999", "https://openalex.org/W6851950068", "https://openalex.org/W6851960618", "https://openalex.org/W6852060543", "https://openalex.org/W6852489829", "https://openalex.org/W6853094705", "https://openalex.org/W6853116092", "https://openalex.org/W6853528422", "https://openalex.org/W6854866820", "https://openalex.org/W6854878091", "https://openalex.org/W6855350031", "https://openalex.org/W6855425132", "https://openalex.org/W6855955516", "https://openalex.org/W6856032414", "https://openalex.org/W6857872576", "https://openalex.org/W6858380932", "https://openalex.org/W6858816293", "https://openalex.org/W6859398714", "https://openalex.org/W6859600322", "https://openalex.org/W6859744083", "https://openalex.org/W6860622411"], "related_works": ["https://openalex.org/W2616627668", "https://openalex.org/W3137121595", "https://openalex.org/W2379392295", "https://openalex.org/W3160965418", "https://openalex.org/W2051345519", "https://openalex.org/W2102157173", "https://openalex.org/W1991530724", "https://openalex.org/W3083087975", "https://openalex.org/W2990774877", "https://openalex.org/W3093339210"], "abstract_inverted_index": {"Multi-modal": [0], "large": [1], "language": [2, 109, 119], "models": [3, 240], "(MLLMs)": [4], "have": [5], "demonstrated": [6], "remarkable": [7], "success": [8], "in": [9, 36, 42, 64, 130, 216, 229], "vision": [10], "and": [11, 27, 81, 87, 108, 111, 118, 185, 196, 210, 241, 250, 261], "visual-language": [12], "tasks": [13, 60, 142, 234], "within": [14], "the": [15, 21, 32, 37, 43, 48, 103, 113, 131, 202, 212, 217, 225, 237, 244, 247], "natural": [16, 26], "image": [17, 70, 146], "domain.": [18, 219], "Owing": [19], "to": [20, 79, 136], "significant": [22], "domain": [23, 39, 133], "gap": [24], "between": [25, 105], "remote": [28], "sensing": [29], "(RS)": [30], "images,": [31], "development": [33, 213], "of": [34, 115, 141, 204, 214, 246], "MLLMs": [35, 205, 215], "RS": [38, 58, 69, 132, 169, 183, 207, 218, 231], "is": [40, 62, 77, 98, 134, 171], "still": [41], "infant": [44], "stage.": [45], "To": [46], "fill": [47], "gap,": [49], "a": [50, 73, 93, 122, 138, 161, 252], "pioneer": [51], "MLLM": [52], "named": [53, 163], "EarthGPT": [54, 249], "integrating": [55], "various": [56, 230], "multi-sensor": [57, 128, 167, 187], "interpretation": [59, 233], "uniformly": [61], "proposed": [63, 135, 248], "this": [65], "paper": [66], "for": [67, 127, 255], "universal": [68], "comprehension.": [71], "Firstly,": [72], "visual-enhanced": [74], "perception": [75, 85, 90, 107], "mechanism": [76], "constructed": [78], "refine": [80], "incorporate": [82], "coarse-scale": [83], "semantic": [84], "information": [86], "fine-scale": [88], "detailed": [89], "information.": [91], "Secondly,": [92], "cross-modal": [94], "mutual": [95], "comprehension": [96, 110, 114], "approach": [97], "proposed,": [99], "aiming": [100], "at": [101, 265], "enhancing": [102], "interplay": [104], "visual": [106, 117, 150, 154, 232], "deepening": [112], "both": [116], "content.": [120], "Finally,": [121], "unified": [123], "instruction": [124], "tuning": [125], "method": [126], "multi-task": [129], "unify": [137], "wide": [139], "range": [140], "including": [143, 186], "scene": [144], "classification,": [145], "captioning,": [147, 149], "region-level": [148], "question": [151], "answering": [152], "(VQA),": [153], "grounding,": [155], "object": [156], "detection,": [157], "etc.": [158], "More": [159], "importantly,": [160], "dataset": [162, 200, 262], "MMRS-1M": [164, 199], "featuring": [165], "large-scale": [166], "multi-modal": [168], "instruction-following": [170], "constructed,": [172], "comprising": [173], "over": [174], "1M": [175], "image-text": [176], "pairs": [177], "based": [178], "on": [179, 206], "34": [180], "existing": [181], "diverse": [182], "datasets": [184], "images": [188], "such": [189], "as": [190], "optical,": [191], "synthetic": [192], "aperture": [193], "radar": [194], "(SAR),": [195], "infrared.": [197], "The": [198], "addresses": [201], "drawback": [203], "expert": [208], "knowledge": [209], "stimulates": [211], "Extensive": [220], "experiments": [221], "are": [222, 263], "conducted,": [223], "demonstrating": [224], "EarthGPT\u2019s": [226], "superior": [227], "performance": [228], "compared": [235], "with": [236], "other": [238], "specialist": [239], "MLLMs,": [242], "proving": [243], "effectiveness": [245], "offering": [251], "versatile": [253], "paradigm": [254], "open-set": [256], "reasoning": [257], "tasks.": [258], "Our": [259], "code": [260], "available": [264], "https://github.com/wivizhang/EarthGPT.": [266]}, "counts_by_year": [{"year": 2026, "cited_by_count": 17}, {"year": 2025, "cited_by_count": 89}, {"year": 2024, "cited_by_count": 25}], "updated_date": "2026-05-20T08:49:12.498775", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4405695223", "doi": "https://doi.org/10.1016/j.inffus.2024.102888", "title": "A comprehensive survey of large language models and multimodal large language models in medicine", "display_name": "A comprehensive survey of large language models and multimodal large language models in medicine", "relevance_score": 1121.8372, "publication_year": 2024, "publication_date": "2024-12-23", "ids": {"openalex": "https://openalex.org/W4405695223", "doi": "https://doi.org/10.1016/j.inffus.2024.102888"}, "language": "en", "primary_location": {"id": "doi:10.1016/j.inffus.2024.102888", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.inffus.2024.102888", "pdf_url": null, "source": {"id": "https://openalex.org/S7560371", "display_name": "Information Fusion", "issn_l": "1566-2535", "issn": ["1566-2535", "1872-6305"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Information Fusion", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5044490010", "display_name": "Hanguang Xiao", "orcid": "https://orcid.org/0000-0002-4359-7455"}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Hanguang Xiao", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": "https://orcid.org/0000-0002-4359-7455", "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113337750", "display_name": "Feizhong Zhou", "orcid": null}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Feizhong Zhou", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5112364223", "display_name": "Xingyue Liu", "orcid": null}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xingyue Liu", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100618135", "display_name": "Tianqi Liu", "orcid": "https://orcid.org/0000-0002-0224-045X"}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tianqi Liu", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100344732", "display_name": "\u0416\u0438\u043f\u0435\u043d\u0433 \u041b\u0438", "orcid": "https://orcid.org/0000-0002-0415-087X"}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhipeng Li", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100352321", "display_name": "Xin Liu", "orcid": "https://orcid.org/0000-0003-2802-594X"}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xin Liu", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101289661", "display_name": "Xiaoxuan Huang", "orcid": null}, "institutions": [{"id": "https://openalex.org/I50632499", "display_name": "Chongqing University of Technology", "ror": "https://ror.org/04vgbd477", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I50632499"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiaoxuan Huang", "raw_affiliation_strings": ["School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401120, China", "institution_ids": ["https://openalex.org/I50632499"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 7, "corresponding_author_ids": ["https://openalex.org/A5044490010"], "corresponding_institution_ids": ["https://openalex.org/I50632499"], "apc_list": {"value": 4650, "currency": "USD", "value_usd": 4650}, "apc_paid": null, "fwci": 22.4377, "has_fulltext": false, "cited_by_count": 71, "citation_normalized_percentile": {"value": 0.99614815, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "117", "issue": null, "first_page": "102888", "last_page": "102888"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9986000061035156, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9986000061035156, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.9958000183105469, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9944000244140625, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.657264769077301}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.37105560302734375}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.32588082551956177}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.657264769077301}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.37105560302734375}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.32588082551956177}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1016/j.inffus.2024.102888", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.inffus.2024.102888", "pdf_url": null, "source": {"id": "https://openalex.org/S7560371", "display_name": "Information Fusion", "issn_l": "1566-2535", "issn": ["1566-2535", "1872-6305"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Information Fusion", "raw_type": "journal-article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.7400000095367432, "display_name": "Quality Education"}], "awards": [{"id": "https://openalex.org/G1258980929", "display_name": null, "funder_award_id": "CSTB2023TIAD-STX0020", "funder_id": "https://openalex.org/F4320323172", "funder_display_name": "Natural Science Foundation of Chongqing"}, {"id": "https://openalex.org/G2122523784", "display_name": null, "funder_award_id": "CSTB2023NSCQ-LZX0068", "funder_id": "https://openalex.org/F4320323172", "funder_display_name": "Natural Science Foundation of Chongqing"}, {"id": "https://openalex.org/G4692072499", "display_name": null, "funder_award_id": "CSTB2024NSCQ-LZX0080", "funder_id": "https://openalex.org/F4320323172", "funder_display_name": "Natural Science Foundation of Chongqing"}, {"id": "https://openalex.org/G5545201110", "display_name": null, "funder_award_id": "62471075", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}, {"id": "https://openalex.org/F4320323172", "display_name": "Natural Science Foundation of Chongqing", "ror": "https://ror.org/01h0zpd94"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 262, "referenced_works": ["https://openalex.org/W1490960179", "https://openalex.org/W1583837637", "https://openalex.org/W1593271688", "https://openalex.org/W1956340063", "https://openalex.org/W2085891931", "https://openalex.org/W2102831150", "https://openalex.org/W2119852447", "https://openalex.org/W2152772232", "https://openalex.org/W2159583324", "https://openalex.org/W2176263492", "https://openalex.org/W2191637929", "https://openalex.org/W2396881363", "https://openalex.org/W2525778437", "https://openalex.org/W2606555609", "https://openalex.org/W2750779823", "https://openalex.org/W2781528640", "https://openalex.org/W2896457183", "https://openalex.org/W2901466771", "https://openalex.org/W2903314293", "https://openalex.org/W2911489562", "https://openalex.org/W2913059114", "https://openalex.org/W2913352150", "https://openalex.org/W2919115771", "https://openalex.org/W2939803556", "https://openalex.org/W2963466845", "https://openalex.org/W2965373594", "https://openalex.org/W2995225687", "https://openalex.org/W2996428491", "https://openalex.org/W3012608737", "https://openalex.org/W3046375318", "https://openalex.org/W3083376569", "https://openalex.org/W3101223450", "https://openalex.org/W3122890974", "https://openalex.org/W3162532547", "https://openalex.org/W3162922479", "https://openalex.org/W3184369217", "https://openalex.org/W3184735396", "https://openalex.org/W3185341429", "https://openalex.org/W3196895296", "https://openalex.org/W3214493799", "https://openalex.org/W4205098185", "https://openalex.org/W4205807230", "https://openalex.org/W4206590911", "https://openalex.org/W4212774754", "https://openalex.org/W4224308101", "https://openalex.org/W4225323055", "https://openalex.org/W4226278401", "https://openalex.org/W4244955044", "https://openalex.org/W4281657280", "https://openalex.org/W4287125738", "https://openalex.org/W4287674181", "https://openalex.org/W4288089799", "https://openalex.org/W4290877962", "https://openalex.org/W4292779060", "https://openalex.org/W4303443398", "https://openalex.org/W4309674289", "https://openalex.org/W4311991106", "https://openalex.org/W4312220150", "https://openalex.org/W4313439128", "https://openalex.org/W4318142410", "https://openalex.org/W4319301505", "https://openalex.org/W4320561779", "https://openalex.org/W4322718191", "https://openalex.org/W4322723456", "https://openalex.org/W4323350039", "https://openalex.org/W4323709074", "https://openalex.org/W4324106550", "https://openalex.org/W4324130227", "https://openalex.org/W4360891289", "https://openalex.org/W4361289889", "https://openalex.org/W4362598952", "https://openalex.org/W4365143687", "https://openalex.org/W4366198844", "https://openalex.org/W4366208220", "https://openalex.org/W4366327625", "https://openalex.org/W4366330503", "https://openalex.org/W4366447635", "https://openalex.org/W4367860620", "https://openalex.org/W4376871976", "https://openalex.org/W4377009978", "https://openalex.org/W4377010595", "https://openalex.org/W4377121462", "https://openalex.org/W4377297670", "https://openalex.org/W4378771755", "https://openalex.org/W4379259189", "https://openalex.org/W4379508361", "https://openalex.org/W4380272254", "https://openalex.org/W4380353786", "https://openalex.org/W4380887490", "https://openalex.org/W4381253519", "https://openalex.org/W4381806419", "https://openalex.org/W4381930847", "https://openalex.org/W4384071683", "https://openalex.org/W4384561707", "https://openalex.org/W4384918448", "https://openalex.org/W4385245566", "https://openalex.org/W4385436553", "https://openalex.org/W4385456320", "https://openalex.org/W4385844672", "https://openalex.org/W4385948838", "https://openalex.org/W4386076522", "https://openalex.org/W4386081793", "https://openalex.org/W4386302153", "https://openalex.org/W4386501272", "https://openalex.org/W4386692532", "https://openalex.org/W4386721614", "https://openalex.org/W4386722137", "https://openalex.org/W4386794639", "https://openalex.org/W4386813249", "https://openalex.org/W4386829267", "https://openalex.org/W4386867830", "https://openalex.org/W4386973901", "https://openalex.org/W4387158222", "https://openalex.org/W4387293242", "https://openalex.org/W4387687904", "https://openalex.org/W4387688013", "https://openalex.org/W4387823622", "https://openalex.org/W4387929270", "https://openalex.org/W4387947536", "https://openalex.org/W4387973771", "https://openalex.org/W4388092223", "https://openalex.org/W4388488349", "https://openalex.org/W4388713229", "https://openalex.org/W4388717680", "https://openalex.org/W4388725043", "https://openalex.org/W4388733340", "https://openalex.org/W4389116614", "https://openalex.org/W4389267014", "https://openalex.org/W4389335347", "https://openalex.org/W4389519219", "https://openalex.org/W4389519275", "https://openalex.org/W4389519920", "https://openalex.org/W4390041933", "https://openalex.org/W4390690017", "https://openalex.org/W4390690043", "https://openalex.org/W4390828922", "https://openalex.org/W4390833194", "https://openalex.org/W4390874575", "https://openalex.org/W4390919701", "https://openalex.org/W4391013432", "https://openalex.org/W4391301614", "https://openalex.org/W4391555991", "https://openalex.org/W4391811667", "https://openalex.org/W4391940656", "https://openalex.org/W4392044798", "https://openalex.org/W4392576158", "https://openalex.org/W4392978897", "https://openalex.org/W4393147125", "https://openalex.org/W4393153123", "https://openalex.org/W4393159297", "https://openalex.org/W4393300262", "https://openalex.org/W4393904064", "https://openalex.org/W4394782456", "https://openalex.org/W4394805876", "https://openalex.org/W4394906055", "https://openalex.org/W4395659193", "https://openalex.org/W4395703766", "https://openalex.org/W4396753423", "https://openalex.org/W4396818380", "https://openalex.org/W4398221084", "https://openalex.org/W4399206078", "https://openalex.org/W4399317923", "https://openalex.org/W4399510493", "https://openalex.org/W4399554422", "https://openalex.org/W4399567248", "https://openalex.org/W4399596965", "https://openalex.org/W4399912840", "https://openalex.org/W4400362569", "https://openalex.org/W4400434448", "https://openalex.org/W4400493343", "https://openalex.org/W4400907075", "https://openalex.org/W4401043272", "https://openalex.org/W4401044130", "https://openalex.org/W4401326040", "https://openalex.org/W4401459163", "https://openalex.org/W4402400689", "https://openalex.org/W4402536012", "https://openalex.org/W4402582321", "https://openalex.org/W4402671009", "https://openalex.org/W4402693738", "https://openalex.org/W4402727764", "https://openalex.org/W4402753980", "https://openalex.org/W4402953710", "https://openalex.org/W4403476856", "https://openalex.org/W4403622706", "https://openalex.org/W4403813762", "https://openalex.org/W4404143589", "https://openalex.org/W4404356490", "https://openalex.org/W4404517435", "https://openalex.org/W4404587067", "https://openalex.org/W4405102058", "https://openalex.org/W4405105409", "https://openalex.org/W6621543089", "https://openalex.org/W6640842352", "https://openalex.org/W6682631176", "https://openalex.org/W6685812147", "https://openalex.org/W6739901393", "https://openalex.org/W6756054306", "https://openalex.org/W6759579507", "https://openalex.org/W6761205521", "https://openalex.org/W6767102903", "https://openalex.org/W6769627184", "https://openalex.org/W6776225533", "https://openalex.org/W6778883912", "https://openalex.org/W6781031682", "https://openalex.org/W6782465632", "https://openalex.org/W6783904465", "https://openalex.org/W6784078253", "https://openalex.org/W6788701349", "https://openalex.org/W6790830454", "https://openalex.org/W6791353385", "https://openalex.org/W6791613716", "https://openalex.org/W6794173217", "https://openalex.org/W6797109355", "https://openalex.org/W6798805250", "https://openalex.org/W6802958121", "https://openalex.org/W6810081322", "https://openalex.org/W6810108873", "https://openalex.org/W6810334672", "https://openalex.org/W6810738896", "https://openalex.org/W6838506385", "https://openalex.org/W6839328737", "https://openalex.org/W6839807890", "https://openalex.org/W6849177959", "https://openalex.org/W6849643969", "https://openalex.org/W6850353666", "https://openalex.org/W6850867085", "https://openalex.org/W6851195955", "https://openalex.org/W6851502328", "https://openalex.org/W6851592950", "https://openalex.org/W6851800889", "https://openalex.org/W6851812084", "https://openalex.org/W6852078084", "https://openalex.org/W6852315413", "https://openalex.org/W6852418670", "https://openalex.org/W6852449896", "https://openalex.org/W6852652685", "https://openalex.org/W6852874933", "https://openalex.org/W6852924361", "https://openalex.org/W6853310435", "https://openalex.org/W6853469104", "https://openalex.org/W6853920016", "https://openalex.org/W6854105909", "https://openalex.org/W6854691855", "https://openalex.org/W6855173278", "https://openalex.org/W6855496480", "https://openalex.org/W6856048081", "https://openalex.org/W6856242815", "https://openalex.org/W6857321105", "https://openalex.org/W6858986594", "https://openalex.org/W6859010493", "https://openalex.org/W6859759945", "https://openalex.org/W6861056325", "https://openalex.org/W6861067382", "https://openalex.org/W6861533627", "https://openalex.org/W6871862530", "https://openalex.org/W6872018063", "https://openalex.org/W6872297623", "https://openalex.org/W6872473154", "https://openalex.org/W6873791297", "https://openalex.org/W6874260675", "https://openalex.org/W6898505805"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2899084033", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W4391913857", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W3204019825"], "abstract_inverted_index": null, "counts_by_year": [{"year": 2026, "cited_by_count": 24}, {"year": 2025, "cited_by_count": 47}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2024-12-23T00:00:00"}, {"id": "https://openalex.org/W4405596328", "doi": "https://doi.org/10.1007/s11432-024-4251-x", "title": "Woodpecker: hallucination correction for multimodal large language models", "display_name": "Woodpecker: hallucination correction for multimodal large language models", "relevance_score": 1113.2958, "publication_year": 2024, "publication_date": "2024-12-01", "ids": {"openalex": "https://openalex.org/W4405596328", "doi": "https://doi.org/10.1007/s11432-024-4251-x"}, "language": "en", "primary_location": {"id": "doi:10.1007/s11432-024-4251-x", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s11432-024-4251-x", "pdf_url": null, "source": {"id": "https://openalex.org/S4210218743", "display_name": "Science China Information Sciences", "issn_l": "1674-733X", "issn": ["1674-733X", "1869-1919"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319965", "host_organization_name": "Springer Nature", "host_organization_lineage": ["https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Science China Information Sciences", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073775343", "display_name": "Shukang Yin", "orcid": "https://orcid.org/0000-0002-5356-1800"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Shukang Yin", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "institution_ids": ["https://openalex.org/I126520041"]}, {"raw_affiliation_string": "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014172220", "display_name": "Chaoyou Fu", "orcid": "https://orcid.org/0000-0002-0079-7668"}, "institutions": [{"id": "https://openalex.org/I308837", "display_name": "Suzhou University of Science and Technology", "ror": "https://ror.org/04en8wb91", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I308837"]}, {"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}, {"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chaoyou Fu", "raw_affiliation_strings": ["School of Intelligence Science and Technology, Nanjing University, Suzhou, 215163, China", "State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China", "Tencent YouTu Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Intelligence Science and Technology, Nanjing University, Suzhou, 215163, China", "institution_ids": ["https://openalex.org/I308837", "https://openalex.org/I881766915"]}, {"raw_affiliation_string": "State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China", "institution_ids": ["https://openalex.org/I881766915"]}, {"raw_affiliation_string": "Tencent YouTu Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100572538", "display_name": "Sirui Zhao", "orcid": null}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Sirui Zhao", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "institution_ids": ["https://openalex.org/I126520041"]}, {"raw_affiliation_string": "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5060550824", "display_name": "Tong Bill Xu", "orcid": "https://orcid.org/0000-0001-6186-5460"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tong Xu", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "institution_ids": ["https://openalex.org/I126520041"]}, {"raw_affiliation_string": "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100704211", "display_name": "Hao Wang", "orcid": "https://orcid.org/0000-0002-3243-487X"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hao Wang", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "institution_ids": ["https://openalex.org/I126520041"]}, {"raw_affiliation_string": "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5031774490", "display_name": "Dianbo Sui", "orcid": "https://orcid.org/0000-0002-5200-2265"}, "institutions": [{"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "funder", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210094879", "display_name": "Shandong Institute of Automation", "ror": "https://ror.org/00qdtba35", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4210094879", "https://openalex.org/I4210142748"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Dianbo Sui", "raw_affiliation_strings": ["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China", "institution_ids": ["https://openalex.org/I4210094879", "https://openalex.org/I19820366"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039883116", "display_name": "Yunhang Shen", "orcid": "https://orcid.org/0000-0002-3970-7519"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}, {"id": "https://openalex.org/I4210132948", "display_name": "Shanghai Chengtou (China)", "ror": "https://ror.org/041rv6v55", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I4210132948"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yunhang Shen", "raw_affiliation_strings": ["YouTu, Shanghai, 200233, China", "Tencent YouTu Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "YouTu, Shanghai, 200233, China", "institution_ids": ["https://openalex.org/I4210132948"]}, {"raw_affiliation_string": "Tencent YouTu Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100655785", "display_name": "Ke Li", "orcid": "https://orcid.org/0000-0001-7199-9139"}, "institutions": [{"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}, {"id": "https://openalex.org/I4210132948", "display_name": "Shanghai Chengtou (China)", "ror": "https://ror.org/041rv6v55", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I4210132948"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ke Li", "raw_affiliation_strings": ["YouTu, Shanghai, 200233, China", "Tencent YouTu Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "YouTu, Shanghai, 200233, China", "institution_ids": ["https://openalex.org/I4210132948"]}, {"raw_affiliation_string": "Tencent YouTu Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101323125", "display_name": "Xing Sun", "orcid": null}, "institutions": [{"id": "https://openalex.org/I4210132948", "display_name": "Shanghai Chengtou (China)", "ror": "https://ror.org/041rv6v55", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I4210132948"]}, {"id": "https://openalex.org/I2250653659", "display_name": "Tencent (China)", "ror": "https://ror.org/00hhjss72", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250653659"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xing Sun", "raw_affiliation_strings": ["YouTu, Shanghai, 200233, China", "Tencent YouTu Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "YouTu, Shanghai, 200233, China", "institution_ids": ["https://openalex.org/I4210132948"]}, {"raw_affiliation_string": "Tencent YouTu Lab", "institution_ids": ["https://openalex.org/I2250653659"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048237545", "display_name": "Enhong Chen", "orcid": "https://orcid.org/0000-0002-4835-4102"}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Enhong Chen", "raw_affiliation_strings": ["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, China", "institution_ids": ["https://openalex.org/I126520041"]}, {"raw_affiliation_string": "School of Data Science, USTC & State Key Laboratory of Cognitive Intelligence", "institution_ids": []}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 10, "corresponding_author_ids": ["https://openalex.org/A5073775343"], "corresponding_institution_ids": ["https://openalex.org/I126520041"], "apc_list": {"value": 2390, "currency": "EUR", "value_usd": 2990}, "apc_paid": null, "fwci": 19.7481, "has_fulltext": false, "cited_by_count": 62, "citation_normalized_percentile": {"value": 0.99511868, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 96, "max": 100}, "biblio": {"volume": "67", "issue": "12", "first_page": null, "last_page": null}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9869999885559082, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9869999885559082, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9394999742507935, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9258000254631042, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/woodpecker", "display_name": "Woodpecker", "score": 0.44309675693511963}, {"id": "https://openalex.org/keywords/psychology", "display_name": "Psychology", "score": 0.4250434637069702}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.40382856130599976}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.389457643032074}, {"id": "https://openalex.org/keywords/cognitive-psychology", "display_name": "Cognitive psychology", "score": 0.34536051750183105}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.3323504328727722}, {"id": "https://openalex.org/keywords/cognitive-science", "display_name": "Cognitive science", "score": 0.32024431228637695}, {"id": "https://openalex.org/keywords/philosophy", "display_name": "Philosophy", "score": 0.197109192609787}, {"id": "https://openalex.org/keywords/ecology", "display_name": "Ecology", "score": 0.11583507061004639}, {"id": "https://openalex.org/keywords/biology", "display_name": "Biology", "score": 0.09028375148773193}], "concepts": [{"id": "https://openalex.org/C2776190662", "wikidata": "https://www.wikidata.org/wiki/Q25439", "display_name": "Woodpecker", "level": 3, "score": 0.44309675693511963}, {"id": "https://openalex.org/C15744967", "wikidata": "https://www.wikidata.org/wiki/Q9418", "display_name": "Psychology", "level": 0, "score": 0.4250434637069702}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.40382856130599976}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.389457643032074}, {"id": "https://openalex.org/C180747234", "wikidata": "https://www.wikidata.org/wiki/Q23373", "display_name": "Cognitive psychology", "level": 1, "score": 0.34536051750183105}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.3323504328727722}, {"id": "https://openalex.org/C188147891", "wikidata": "https://www.wikidata.org/wiki/Q147638", "display_name": "Cognitive science", "level": 1, "score": 0.32024431228637695}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.197109192609787}, {"id": "https://openalex.org/C18903297", "wikidata": "https://www.wikidata.org/wiki/Q7150", "display_name": "Ecology", "level": 1, "score": 0.11583507061004639}, {"id": "https://openalex.org/C86803240", "wikidata": "https://www.wikidata.org/wiki/Q420", "display_name": "Biology", "level": 0, "score": 0.09028375148773193}, {"id": "https://openalex.org/C185933670", "wikidata": "https://www.wikidata.org/wiki/Q52105", "display_name": "Habitat", "level": 2, "score": 0.0}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1007/s11432-024-4251-x", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s11432-024-4251-x", "pdf_url": null, "source": {"id": "https://openalex.org/S4210218743", "display_name": "Science China Information Sciences", "issn_l": "1674-733X", "issn": ["1674-733X", "1869-1919"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310319965", "host_organization_name": "Springer Nature", "host_organization_lineage": ["https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Science China Information Sciences", "raw_type": "journal-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 49, "referenced_works": ["https://openalex.org/W2186222003", "https://openalex.org/W2593713917", "https://openalex.org/W2606555609", "https://openalex.org/W2898875342", "https://openalex.org/W3027879771", "https://openalex.org/W3083182073", "https://openalex.org/W3134144764", "https://openalex.org/W4225933709", "https://openalex.org/W4226082499", "https://openalex.org/W4290771878", "https://openalex.org/W4309805219", "https://openalex.org/W4309878869", "https://openalex.org/W4318718936", "https://openalex.org/W4321649215", "https://openalex.org/W4322718421", "https://openalex.org/W4323323799", "https://openalex.org/W4323717348", "https://openalex.org/W4323921464", "https://openalex.org/W4324128075", "https://openalex.org/W4324321291", "https://openalex.org/W4353113046", "https://openalex.org/W4353114822", "https://openalex.org/W4361866031", "https://openalex.org/W4366566341", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4375869762", "https://openalex.org/W4377121433", "https://openalex.org/W4378510496", "https://openalex.org/W4378942772", "https://openalex.org/W4382142077", "https://openalex.org/W4382323090", "https://openalex.org/W4386185344", "https://openalex.org/W4386185600", "https://openalex.org/W4386302587", "https://openalex.org/W4388304009", "https://openalex.org/W4388684828", "https://openalex.org/W4389157107", "https://openalex.org/W4389218156", "https://openalex.org/W4391650137", "https://openalex.org/W4393387578", "https://openalex.org/W4399061509", "https://openalex.org/W4404356490", "https://openalex.org/W6778883912", "https://openalex.org/W6851578965", "https://openalex.org/W6851592950", "https://openalex.org/W6851813333", "https://openalex.org/W6857162426", "https://openalex.org/W6858268588"], "related_works": ["https://openalex.org/W1601851233", "https://openalex.org/W2186786304", "https://openalex.org/W2553609535", "https://openalex.org/W2332982260", "https://openalex.org/W2744495894", "https://openalex.org/W2981602727", "https://openalex.org/W2941105321", "https://openalex.org/W2027592706", "https://openalex.org/W2617299444", "https://openalex.org/W2092380747"], "abstract_inverted_index": null, "counts_by_year": [{"year": 2026, "cited_by_count": 12}, {"year": 2025, "cited_by_count": 47}, {"year": 2024, "cited_by_count": 3}], "updated_date": "2026-05-17T08:19:37.847499", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402670262", "doi": "https://doi.org/10.18653/v1/2024.findings-acl.807", "title": "The Revolution of Multimodal Large Language Models: A Survey", "display_name": "The Revolution of Multimodal Large Language Models: A Survey", "relevance_score": 1088.2748, "publication_year": 2024, "publication_date": "2024-01-01", "ids": {"openalex": "https://openalex.org/W4402670262", "doi": "https://doi.org/10.18653/v1/2024.findings-acl.807"}, "language": "en", "primary_location": {"id": "doi:10.18653/v1/2024.findings-acl.807", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.807", "pdf_url": "https://aclanthology.org/2024.findings-acl.807.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://aclanthology.org/2024.findings-acl.807.pdf", "any_repository_has_fulltext": null}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5092738147", "display_name": "Davide Caffagni", "orcid": "https://orcid.org/0009-0002-3279-6480"}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Davide Caffagni", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5092741302", "display_name": "Federico Cocchi", "orcid": "https://orcid.org/0009-0005-1396-9114"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Federico Cocchi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5035092680", "display_name": "Luca Barsellotti", "orcid": "https://orcid.org/0000-0001-8845-8523"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luca Barsellotti", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5090402362", "display_name": "Nicholas Moratelli", "orcid": "https://orcid.org/0000-0001-9362-5680"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nicholas Moratelli", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5033144993", "display_name": "Sara Sarto", "orcid": "https://orcid.org/0000-0003-1057-3374"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sara Sarto", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5048928616", "display_name": "Lorenzo Baraldi", "orcid": "https://orcid.org/0000-0001-5125-4957"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lorenzo Baraldi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5048928616", "display_name": "Lorenzo Baraldi", "orcid": "https://orcid.org/0000-0001-5125-4957"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lorenzo Baraldi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5066519737", "display_name": "Marcella Cornia", "orcid": "https://orcid.org/0000-0001-9640-9385"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Marcella Cornia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030948871", "display_name": "Rita Cucchiara", "orcid": "https://orcid.org/0000-0002-2239-283X"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rita Cucchiara", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 9, "corresponding_author_ids": ["https://openalex.org/A5092738147"], "corresponding_institution_ids": [], "apc_list": null, "apc_paid": null, "fwci": 20.2946, "has_fulltext": true, "cited_by_count": 64, "citation_normalized_percentile": {"value": 0.99533121, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 98, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "13590", "last_page": "13618"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9668999910354614, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9668999910354614, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9517999887466431, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6758253574371338}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.3822833299636841}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.33054065704345703}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6758253574371338}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.3822833299636841}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.33054065704345703}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.18653/v1/2024.findings-acl.807", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.807", "pdf_url": "https://aclanthology.org/2024.findings-acl.807.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}], "best_oa_location": {"id": "doi:10.18653/v1/2024.findings-acl.807", "is_oa": true, "landing_page_url": "https://doi.org/10.18653/v1/2024.findings-acl.807", "pdf_url": "https://aclanthology.org/2024.findings-acl.807.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Findings of the Association for Computational Linguistics ACL 2024", "raw_type": "proceedings-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.46000000834465027, "display_name": "Quality Education"}], "awards": [{"id": "https://openalex.org/G1016895160", "display_name": null, "funder_award_id": "PNRR-M4C2", "funder_id": "https://openalex.org/F4320320300", "funder_display_name": "European Commission"}, {"id": "https://openalex.org/G4508289328", "display_name": null, "funder_award_id": "PE00000013", "funder_id": "https://openalex.org/F4320320300", "funder_display_name": "European Commission"}], "funders": [{"id": "https://openalex.org/F4320320300", "display_name": "European Commission", "ror": "https://ror.org/00k4n6c32"}], "has_content": {"pdf": true, "grobid_xml": false}, "content_urls": {"pdf": "https://content.openalex.org/works/W4402670262.pdf"}, "referenced_works_count": 0, "referenced_works": [], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052", "https://openalex.org/W2382290278", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"Davide": [0], "Caffagni,": [1], "Federico": [2], "Cocchi,": [3], "Luca": [4], "Barsellotti,": [5], "Nicholas": [6], "Moratelli,": [7], "Sara": [8], "Sarto,": [9], "Lorenzo": [10, 12], "Baraldi,": [11, 13], "Marcella": [14], "Cornia,": [15], "Rita": [16], "Cucchiara.": [17], "Findings": [18], "of": [19], "the": [20], "Association": [21], "for": [22], "Computational": [23], "Linguistics:": [24], "ACL": [25], "2024.": [26, 27]}, "counts_by_year": [{"year": 2026, "cited_by_count": 18}, {"year": 2025, "cited_by_count": 39}, {"year": 2024, "cited_by_count": 7}], "updated_date": "2026-05-20T08:49:12.498775", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402727272", "doi": "https://doi.org/10.1109/cvpr52733.2024.01357", "title": "TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding", "display_name": "TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding", "relevance_score": 1021.8959, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402727272", "doi": "https://doi.org/10.1109/cvpr52733.2024.01357"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.01357", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01357", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101030723", "display_name": "Shuhuai Ren", "orcid": "https://orcid.org/0009-0001-9998-864X"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Shuhuai Ren", "raw_affiliation_strings": ["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100599428", "display_name": "Linli Yao", "orcid": "https://orcid.org/0000-0002-9809-8864"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Linli Yao", "raw_affiliation_strings": ["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100723942", "display_name": "Shicheng Li", "orcid": "https://orcid.org/0000-0002-5893-8822"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shicheng Li", "raw_affiliation_strings": ["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101441137", "display_name": "Xu Sun", "orcid": "https://orcid.org/0000-0001-8241-9320"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xu Sun", "raw_affiliation_strings": ["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5104232416", "display_name": "Lu Hou", "orcid": "https://orcid.org/0009-0006-0550-4517"}, "institutions": [{"id": "https://openalex.org/I4210159102", "display_name": "Huawei Technologies (Sweden)", "ror": "https://ror.org/0500fyd17", "country_code": "SE", "type": "company", "lineage": ["https://openalex.org/I2250955327", "https://openalex.org/I4210159102"]}], "countries": ["SE"], "is_corresponding": false, "raw_author_name": "Lu Hou", "raw_affiliation_strings": ["Huawei Noah&#x0027;s Ark Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Noah&#x0027;s Ark Lab", "institution_ids": ["https://openalex.org/I4210159102"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 5, "corresponding_author_ids": ["https://openalex.org/A5101030723"], "corresponding_institution_ids": ["https://openalex.org/I20231570"], "apc_list": null, "apc_paid": null, "fwci": 19.9711, "has_fulltext": false, "cited_by_count": 88, "citation_normalized_percentile": {"value": 0.99695133, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "14313", "last_page": "14323"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11439", "display_name": "Video Analysis and Summarization", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11439", "display_name": "Video Analysis and Summarization", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9986000061035156, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10812", "display_name": "Human Pose and Action Recognition", "score": 0.9940999746322632, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.7303394079208374}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.3397940397262573}, {"id": "https://openalex.org/keywords/human\u2013computer-interaction", "display_name": "Human\u2013computer interaction", "score": 0.33936095237731934}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.3290674090385437}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.7303394079208374}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.3397940397262573}, {"id": "https://openalex.org/C107457646", "wikidata": "https://www.wikidata.org/wiki/Q207434", "display_name": "Human\u2013computer interaction", "level": 1, "score": 0.33936095237731934}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.3290674090385437}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.01357", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01357", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [{"id": "https://openalex.org/G4370721888", "display_name": null, "funder_award_id": "62176002", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 75, "referenced_works": ["https://openalex.org/W1924343884", "https://openalex.org/W2525579820", "https://openalex.org/W2529272619", "https://openalex.org/W2952132648", "https://openalex.org/W2963017553", "https://openalex.org/W2963916161", "https://openalex.org/W2963919999", "https://openalex.org/W2964089981", "https://openalex.org/W2964094654", "https://openalex.org/W3115868806", "https://openalex.org/W3161945002", "https://openalex.org/W3168867926", "https://openalex.org/W3176013197", "https://openalex.org/W3177173029", "https://openalex.org/W3186024896", "https://openalex.org/W3205786327", "https://openalex.org/W3210314917", "https://openalex.org/W4214663214", "https://openalex.org/W4226278401", "https://openalex.org/W4312544061", "https://openalex.org/W4312683960", "https://openalex.org/W4312748990", "https://openalex.org/W4312864639", "https://openalex.org/W4318718936", "https://openalex.org/W4322718191", "https://openalex.org/W4361194507", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4376167553", "https://openalex.org/W4376312115", "https://openalex.org/W4376653927", "https://openalex.org/W4380135847", "https://openalex.org/W4380559123", "https://openalex.org/W4384918448", "https://openalex.org/W4385569871", "https://openalex.org/W4385570016", "https://openalex.org/W4385570412", "https://openalex.org/W4386057806", "https://openalex.org/W4386065689", "https://openalex.org/W4386066385", "https://openalex.org/W4386075592", "https://openalex.org/W4386083094", "https://openalex.org/W4387595583", "https://openalex.org/W4388444668", "https://openalex.org/W4388716334", "https://openalex.org/W4389217538", "https://openalex.org/W4389519526", "https://openalex.org/W4389519587", "https://openalex.org/W4389523832", "https://openalex.org/W4390873341", "https://openalex.org/W4402671548", "https://openalex.org/W4402702917", "https://openalex.org/W6785957266", "https://openalex.org/W6791353385", "https://openalex.org/W6799428148", "https://openalex.org/W6800850145", "https://openalex.org/W6802360106", "https://openalex.org/W6810738896", "https://openalex.org/W6847413556", "https://openalex.org/W6849177959", "https://openalex.org/W6850625674", "https://openalex.org/W6850991314", "https://openalex.org/W6851592950", "https://openalex.org/W6851950068", "https://openalex.org/W6852776751", "https://openalex.org/W6852952677", "https://openalex.org/W6853116092", "https://openalex.org/W6853299509", "https://openalex.org/W6853515732", "https://openalex.org/W6854866820", "https://openalex.org/W6854917811", "https://openalex.org/W6857104365", "https://openalex.org/W6857999865", "https://openalex.org/W6858817466", "https://openalex.org/W6859116743"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052", "https://openalex.org/W2382290278", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"This": [0], "work": [1], "proposes": [2], "TimeChat,": [3], "a": [4, 24, 40, 46, 69, 141], "time-sensitive": [5], "multi-modal": [6], "large": [7, 132], "language": [8, 133], "model": [9, 17], "specifically": [10], "designed": [11], "for": [12, 145], "long": [13], "video": [14, 42, 47, 84, 131, 143, 147], "understanding.": [15], "Our": [16], "incorporates": [18], "two": [19], "key": [20], "architectural": [21], "contributions:": [22], "(1)": [23], "timestamp-aware": [25], "frame": [26], "encoder": [27], "that": [28, 44], "binds": [29], "visual": [30], "content": [31], "with": [32], "the": [33, 136], "timestamp": [34], "of": [35, 50, 56, 71], "each": [36], "frame,": [37], "and": [38, 68, 93, 102, 112, 121, 150, 160], "(2)": [39], "sliding": [41], "Q-Former": [43], "produces": [45], "token": [48], "sequence": [49], "varying": [51], "lengths": [52], "to": [53, 74, 129, 138], "accommodate": [54], "videos": [55], "various": [57, 83], "durations.": [58], "Additionally,": [59], "we": [60], "construct": [61], "an": [62], "instruction-tuning": [63], "dataset,": [64], "encompassing": [65], "6": [66], "tasks": [67, 149], "total": [70], "125K": [72], "instances,": [73], "further": [75], "enhance": [76], "TimeChat's": [77, 97], "instruction-following": [78], "performance.": [79], "Experiment": [80], "results": [81], "across": [82], "understanding": [85], "tasks,": [86], "such": [87], "as": [88, 140], "dense": [89], "captioning,": [90], "temporal": [91, 100], "grounding,": [92], "highlight": [94], "detection,": [95], "demonstrate": [96], "strong": [98], "zero-shot": [99], "localization": [101], "reasoning": [103], "capabilities.": [104], "For": [105], "example,": [106], "it": [107], "achieves": [108], "+9.2": [109], "F1": [110], "score": [111], "+2.8": [113], "CIDEr": [114], "on": [115, 119, 126], "YouCook2,": [116], "+5.8": [117], "HIT@1": [118], "QVHighlights,": [120], "+27.5": [122], "R@1": [123], "(I": [124], "oU=0.5)": [125], "Charades-STA,": [127], "compared": [128], "state-of-the-art": [130], "models,": [134], "holding": [135], "potential": [137], "serve": [139], "versatile": [142], "assistant": [144], "long-form": [146], "comprehension": [148], "satisfy": [151], "realistic": [152], "user": [153], "requirements.<sup": [154], "xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"": [155, 157], "xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup": [156], "xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Our": [158], "code": [159], "dataset": [161], "are": [162], "available": [163], "at": [164], "https://github.com/RenShuhuai-Andy/TimeChat.": [165]}, "counts_by_year": [{"year": 2026, "cited_by_count": 17}, {"year": 2025, "cited_by_count": 59}, {"year": 2024, "cited_by_count": 12}], "updated_date": "2026-05-16T08:24:45.110214", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402727730", "doi": "https://doi.org/10.1109/cvpr52733.2024.01710", "title": "ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation", "display_name": "ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation", "relevance_score": 974.34186, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402727730", "doi": "https://doi.org/10.1109/cvpr52733.2024.01710"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.01710", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01710", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5012981856", "display_name": "Xiaoqi Li", "orcid": "https://orcid.org/0000-0001-8855-7759"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xiaoqi Li", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101810713", "display_name": "Mingxu Zhang", "orcid": "https://orcid.org/0000-0002-2509-8812"}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Mingxu Zhang", "raw_affiliation_strings": ["Beijing University of Posts and Telecommunications"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Beijing University of Posts and Telecommunications", "institution_ids": ["https://openalex.org/I139759216"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5027669476", "display_name": "Yiran Geng", "orcid": "https://orcid.org/0000-0003-2440-6438"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yiran Geng", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101608439", "display_name": "Haoran Geng", "orcid": "https://orcid.org/0009-0008-6402-6804"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Haoran Geng", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049786228", "display_name": "Yuxing Long", "orcid": "https://orcid.org/0009-0006-3246-459X"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuxing Long", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003395657", "display_name": "Yan Shen", "orcid": "https://orcid.org/0000-0002-8045-6926"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yan Shen", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050285051", "display_name": "Renrui Zhang", "orcid": null}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Renrui Zhang", "raw_affiliation_strings": ["CUHK,MMLab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK,MMLab", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100440967", "display_name": "Jiaming Liu", "orcid": "https://orcid.org/0000-0002-0257-2091"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiaming Liu", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100389347", "display_name": "Hao Dong", "orcid": "https://orcid.org/0000-0002-0132-0239"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hao Dong", "raw_affiliation_strings": ["School of Computer Science, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 9, "corresponding_author_ids": ["https://openalex.org/A5012981856"], "corresponding_institution_ids": ["https://openalex.org/I20231570"], "apc_list": null, "apc_paid": null, "fwci": 14.6538, "has_fulltext": false, "cited_by_count": 63, "citation_normalized_percentile": {"value": 0.99450469, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 98, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "18061", "last_page": "18070"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10653", "display_name": "Robot Manipulation and Learning", "score": 0.9994000196456909, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.9854999780654907, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/embodied-cognition", "display_name": "Embodied cognition", "score": 0.9069044589996338}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6964111328125}, {"id": "https://openalex.org/keywords/object", "display_name": "Object (grammar)", "score": 0.562028169631958}, {"id": "https://openalex.org/keywords/human\u2013computer-interaction", "display_name": "Human\u2013computer interaction", "score": 0.4990823268890381}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.4211188852787018}, {"id": "https://openalex.org/keywords/cognitive-science", "display_name": "Cognitive science", "score": 0.36591947078704834}, {"id": "https://openalex.org/keywords/psychology", "display_name": "Psychology", "score": 0.15016448497772217}], "concepts": [{"id": "https://openalex.org/C100609095", "wikidata": "https://www.wikidata.org/wiki/Q1335050", "display_name": "Embodied cognition", "level": 2, "score": 0.9069044589996338}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6964111328125}, {"id": "https://openalex.org/C2781238097", "wikidata": "https://www.wikidata.org/wiki/Q175026", "display_name": "Object (grammar)", "level": 2, "score": 0.562028169631958}, {"id": "https://openalex.org/C107457646", "wikidata": "https://www.wikidata.org/wiki/Q207434", "display_name": "Human\u2013computer interaction", "level": 1, "score": 0.4990823268890381}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.4211188852787018}, {"id": "https://openalex.org/C188147891", "wikidata": "https://www.wikidata.org/wiki/Q147638", "display_name": "Cognitive science", "level": 1, "score": 0.36591947078704834}, {"id": "https://openalex.org/C15744967", "wikidata": "https://www.wikidata.org/wiki/Q9418", "display_name": "Psychology", "level": 0, "score": 0.15016448497772217}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.01710", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01710", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [{"id": "https://openalex.org/G3598382722", "display_name": null, "funder_award_id": "62136001", "funder_id": "https://openalex.org/F4320321001", "funder_display_name": "National Natural Science Foundation of China"}], "funders": [{"id": "https://openalex.org/F4320321001", "display_name": "National Natural Science Foundation of China", "ror": "https://ror.org/01h0zpd94"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 53, "referenced_works": ["https://openalex.org/W2745461083", "https://openalex.org/W2961368225", "https://openalex.org/W2963383024", "https://openalex.org/W2990747716", "https://openalex.org/W3035624836", "https://openalex.org/W3092037789", "https://openalex.org/W3095319910", "https://openalex.org/W3168867926", "https://openalex.org/W3173701235", "https://openalex.org/W3186672455", "https://openalex.org/W3199614037", "https://openalex.org/W4221143046", "https://openalex.org/W4225323055", "https://openalex.org/W4283785166", "https://openalex.org/W4322718191", "https://openalex.org/W4361229539", "https://openalex.org/W4366330503", "https://openalex.org/W4378505295", "https://openalex.org/W4378505315", "https://openalex.org/W4379958229", "https://openalex.org/W4383108731", "https://openalex.org/W4384264726", "https://openalex.org/W4385430679", "https://openalex.org/W4385473486", "https://openalex.org/W4386065846", "https://openalex.org/W4386071465", "https://openalex.org/W4386072455", "https://openalex.org/W4387323024", "https://openalex.org/W4387964188", "https://openalex.org/W4388482629", "https://openalex.org/W4390872441", "https://openalex.org/W4390872920", "https://openalex.org/W4390873239", "https://openalex.org/W4401416961", "https://openalex.org/W4402354115", "https://openalex.org/W6791353385", "https://openalex.org/W6796568516", "https://openalex.org/W6796581206", "https://openalex.org/W6799458897", "https://openalex.org/W6809646742", "https://openalex.org/W6810334672", "https://openalex.org/W6811013733", "https://openalex.org/W6850625674", "https://openalex.org/W6851592950", "https://openalex.org/W6851948999", "https://openalex.org/W6852754536", "https://openalex.org/W6853130677", "https://openalex.org/W6853688100", "https://openalex.org/W6854929498", "https://openalex.org/W6857066902", "https://openalex.org/W6857278896", "https://openalex.org/W6857294093", "https://openalex.org/W6859338542"], "related_works": ["https://openalex.org/W2380179524", "https://openalex.org/W4283365723", "https://openalex.org/W2753017648", "https://openalex.org/W2513760693", "https://openalex.org/W2062819913", "https://openalex.org/W2149544884", "https://openalex.org/W2133485962", "https://openalex.org/W2001662723", "https://openalex.org/W4211188312", "https://openalex.org/W4246694033"], "abstract_inverted_index": {"Robot": [0], "manipulation": [1, 46, 176], "relies": [2], "on": [3, 20], "accurately": [4], "predicting": [5], "contact": [6, 145], "points": [7], "and": [8, 63, 78, 108, 129, 192, 202], "end-effector": [9], "directions": [10], "to": [11, 29, 59, 112, 132, 155, 177, 183], "ensure": [12], "successful": [13], "operation.": [14], "However,": [15], "learning-based": [16], "robot": [17, 45], "manipulation,": [18], "trained": [19], "a": [21, 25, 161, 170], "limited": [22], "category": [23, 103], "within": [24], "simulator,": [26], "often": [27], "struggles": [28], "achieve": [30], "generalizability,": [31], "especially": [32], "when": [33], "confronted": [34], "with": [35, 87], "extensive": [36], "categories.": [37], "Therefore,": [38], "we": [39, 72, 168], "introduce": [40], "an": [41, 126, 148], "innovative": [42], "approach": [43, 124], "for": [44, 90, 175], "that": [47], "leverages": [48], "the": [49, 61, 69, 74, 82, 88, 97, 114, 134, 143, 157, 179, 184, 195], "robust": [50], "reasoning": [51, 79, 115], "capabilities": [52], "of": [53, 65, 81, 117, 140, 198], "Multimodal": [54], "Large": [55], "Language": [56], "Models": [57], "(MLLMs)": [58], "enhance": [60], "stability": [62], "generalization": [64], "manipulation.": [66, 91, 120], "By": [67], "fine-tuning": [68, 99], "injected": [70], "adapters,": [71], "preserve": [73], "inherent": [75], "common": [76], "sense": [77], "ability": [80, 89, 116], "MLLMs": [83], "while": [84], "equipping": [85], "them": [86], "The": [92], "fundamental": [93], "insight": [94], "lies": [95], "in": [96, 119, 138, 160, 165, 190], "introduced": [98, 154], "paradigm,": [100], "encompassing": [101], "object": [102], "understanding,": [104], "affordance": [105], "prior": [106], "reasoning,": [107], "object-centric": [109], "pose": [110, 137], "prediction": [111], "stimulate": [113], "MLLM": [118], "During": [121], "inference,": [122], "our": [123], "utilizes": [125], "RGB": [127], "image": [128], "text": [130], "prompt": [131], "predict": [133], "end": [135], "effector's": [136], "chain": [139], "thoughts.": [141], "After": [142], "initial": [144], "is": [146, 153], "established,": [147], "active": [149], "impedance": [150], "adaptation": [151, 172], "policy": [152], "plan": [156], "upcoming": [158], "way-points": [159], "closed-loop": [162], "manner.": [163], "Moreover,": [164], "real": [166], "world,": [167], "design": [169], "test-time": [171], "(TTA)": [173], "strategy": [174], "enable": [178], "model": [180], "better": [181], "adapt": [182], "current": [185], "real-world": [186, 193], "scene": [187], "configuration.": [188], "Experiments": [189], "simulator": [191], "show": [194], "promising": [196], "performance": [197], "Mani-pLLM.": [199], "More": [200], "details": [201], "demonstrations": [203], "can": [204], "be": [205], "found": [206], "at": [207], "https://sites.google.com/view/manipllm.": [208]}, "counts_by_year": [{"year": 2026, "cited_by_count": 11}, {"year": 2025, "cited_by_count": 47}, {"year": 2024, "cited_by_count": 5}], "updated_date": "2026-05-05T08:41:31.759640", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4392915068", "doi": "https://doi.org/10.1001/jama.2023.27861", "title": "Comparative Analysis of Multimodal Large Language Model Performance on Clinical Vignette Questions", "display_name": "Comparative Analysis of Multimodal Large Language Model Performance on Clinical Vignette Questions", "relevance_score": 961.2264, "publication_year": 2024, "publication_date": "2024-03-18", "ids": {"openalex": "https://openalex.org/W4392915068", "doi": "https://doi.org/10.1001/jama.2023.27861", "pmid": "https://pubmed.ncbi.nlm.nih.gov/38497956"}, "language": "en", "primary_location": {"id": "doi:10.1001/jama.2023.27861", "is_oa": false, "landing_page_url": "https://doi.org/10.1001/jama.2023.27861", "pdf_url": null, "source": {"id": "https://openalex.org/S172573765", "display_name": "JAMA", "issn_l": "0098-7484", "issn": ["0098-7484", "1538-3598"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320259", "host_organization_name": "American Medical Association", "host_organization_lineage": ["https://openalex.org/P4310320259"], "host_organization_lineage_names": ["American Medical Association"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "JAMA", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref", "pubmed"], "open_access": {"is_oa": true, "oa_status": "green", "oa_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/10949144", "any_repository_has_fulltext": true}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5018843444", "display_name": "Tianyu Han", "orcid": "https://orcid.org/0000-0002-8636-6462"}, "institutions": [{"id": "https://openalex.org/I4210120689", "display_name": "Universit\u00e4tsklinikum Aachen", "ror": "https://ror.org/02gm5zw39", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I4210120689"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Tianyu Han", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany", "institution_ids": ["https://openalex.org/I4210120689"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005164520", "display_name": "Lisa C. Adams", "orcid": "https://orcid.org/0000-0001-5836-4542"}, "institutions": [{"id": "https://openalex.org/I62916508", "display_name": "Technical University of Munich", "ror": "https://ror.org/02kkvpp62", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I62916508"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Lisa C. Adams", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, Technical University of Munich, Munich, Germany", "institution_ids": ["https://openalex.org/I62916508"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5006318966", "display_name": "Keno K. Bressem", "orcid": "https://orcid.org/0000-0001-9249-8624"}, "institutions": [{"id": "https://openalex.org/I7877124", "display_name": "Charit\u00e9 - Universit\u00e4tsmedizin Berlin", "ror": "https://ror.org/001w7jn25", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I7877124"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Keno K. Bressem", "raw_affiliation_strings": ["Department of Radiology, Charit\u00e9 Universit\u00e4tsmedizin Berlin, Berlin, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Charit\u00e9 Universit\u00e4tsmedizin Berlin, Berlin, Germany", "institution_ids": ["https://openalex.org/I7877124"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5028916711", "display_name": "Felix Busch", "orcid": "https://orcid.org/0000-0001-9770-8555"}, "institutions": [{"id": "https://openalex.org/I7877124", "display_name": "Charit\u00e9 - Universit\u00e4tsmedizin Berlin", "ror": "https://ror.org/001w7jn25", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I7877124"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Felix Busch", "raw_affiliation_strings": ["Department of Radiology, Charit\u00e9 Universit\u00e4tsmedizin Berlin, Berlin, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Charit\u00e9 Universit\u00e4tsmedizin Berlin, Berlin, Germany", "institution_ids": ["https://openalex.org/I7877124"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091689170", "display_name": "Sven Nebelung", "orcid": "https://orcid.org/0000-0002-5267-9962"}, "institutions": [{"id": "https://openalex.org/I4210120689", "display_name": "Universit\u00e4tsklinikum Aachen", "ror": "https://ror.org/02gm5zw39", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I4210120689"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Sven Nebelung", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany", "institution_ids": ["https://openalex.org/I4210120689"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5016512818", "display_name": "Daniel Truhn", "orcid": "https://orcid.org/0000-0002-9605-0728"}, "institutions": [{"id": "https://openalex.org/I4210120689", "display_name": "Universit\u00e4tsklinikum Aachen", "ror": "https://ror.org/02gm5zw39", "country_code": "DE", "type": "healthcare", "lineage": ["https://openalex.org/I4210120689"]}], "countries": ["DE"], "is_corresponding": true, "raw_author_name": "Daniel Truhn", "raw_affiliation_strings": ["Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany", "institution_ids": ["https://openalex.org/I4210120689"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 6, "corresponding_author_ids": ["https://openalex.org/A5016512818"], "corresponding_institution_ids": ["https://openalex.org/I4210120689"], "apc_list": null, "apc_paid": null, "fwci": 8.2687, "has_fulltext": false, "cited_by_count": 77, "citation_normalized_percentile": {"value": 0.98024465, "is_in_top_1_percent": false, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "331", "issue": "15", "first_page": "1320", "last_page": "1320"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9962999820709229, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9962999820709229, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T12574", "display_name": "Clinical Reasoning and Diagnostic Skills", "score": 0.9714999794960022, "subfield": {"id": "https://openalex.org/subfields/2714", "display_name": "Family Practice"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.9567999839782715, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/medicine", "display_name": "Medicine", "score": 0.9568617343902588}, {"id": "https://openalex.org/keywords/vignette", "display_name": "Vignette", "score": 0.8355904817581177}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.4198184609413147}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.4024263024330139}, {"id": "https://openalex.org/keywords/statistics", "display_name": "Statistics", "score": 0.1343022882938385}], "concepts": [{"id": "https://openalex.org/C71924100", "wikidata": "https://www.wikidata.org/wiki/Q11190", "display_name": "Medicine", "level": 0, "score": 0.9568617343902588}, {"id": "https://openalex.org/C9719361", "wikidata": "https://www.wikidata.org/wiki/Q7928967", "display_name": "Vignette", "level": 2, "score": 0.8355904817581177}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.4198184609413147}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.4024263024330139}, {"id": "https://openalex.org/C105795698", "wikidata": "https://www.wikidata.org/wiki/Q12483", "display_name": "Statistics", "level": 1, "score": 0.1343022882938385}, {"id": "https://openalex.org/C33923547", "wikidata": "https://www.wikidata.org/wiki/Q395", "display_name": "Mathematics", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.0}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.0}], "mesh": [{"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D001185", "descriptor_name": "Artificial Intelligence", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D003952", "descriptor_name": "Diagnostic Imaging", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D003952", "descriptor_name": "Diagnostic Imaging", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D003952", "descriptor_name": "Diagnostic Imaging", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D003952", "descriptor_name": "Diagnostic Imaging", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D007802", "descriptor_name": "Language", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": false}, {"descriptor_ui": "D008487", "descriptor_name": "Medical History Taking", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D008487", "descriptor_name": "Medical History Taking", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D008487", "descriptor_name": "Medical History Taking", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}, {"descriptor_ui": "D008487", "descriptor_name": "Medical History Taking", "qualifier_ui": null, "qualifier_name": null, "is_major_topic": true}], "locations_count": 5, "locations": [{"id": "doi:10.1001/jama.2023.27861", "is_oa": false, "landing_page_url": "https://doi.org/10.1001/jama.2023.27861", "pdf_url": null, "source": {"id": "https://openalex.org/S172573765", "display_name": "JAMA", "issn_l": "0098-7484", "issn": ["0098-7484", "1538-3598"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320259", "host_organization_name": "American Medical Association", "host_organization_lineage": ["https://openalex.org/P4310320259"], "host_organization_lineage_names": ["American Medical Association"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "JAMA", "raw_type": "journal-article"}, {"id": "pmid:38497956", "is_oa": false, "landing_page_url": "https://pubmed.ncbi.nlm.nih.gov/38497956", "pdf_url": null, "source": {"id": "https://openalex.org/S4306525036", "display_name": "PubMed", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "JAMA", "raw_type": null}, {"id": "pmh:oai:pubmedcentral.nih.gov:10949144", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/10949144", "pdf_url": null, "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "JAMA", "raw_type": "Text"}, {"id": "pmh:oai:mediatum.ub.tum.de:node/1738922", "is_oa": false, "landing_page_url": "https://mediatum.ub.tum.de/1738922", "pdf_url": null, "source": {"id": "https://openalex.org/S4377196330", "display_name": "mediaTUM  (Technical University of Munich)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I62916508", "host_organization_name": "Technical University of Munich", "host_organization_lineage": ["https://openalex.org/I62916508"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "", "raw_type": "article"}, {"id": "pmh:oai:publications.rwth-aachen.de:1007138", "is_oa": false, "landing_page_url": "https://publications.rwth-aachen.de/record/1007138", "pdf_url": null, "source": {"id": "https://openalex.org/S4306401033", "display_name": "RWTH Publications (RWTH Aachen)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I887968799", "host_organization_name": "RWTH Aachen University", "host_organization_lineage": ["https://openalex.org/I887968799"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "The journal of the American Medical Association 331(15), 1320-1321 (2024). doi:10.1001/jama.2023.27861", "raw_type": "info:eu-repo/semantics/publishedVersion"}], "best_oa_location": {"id": "pmh:oai:pubmedcentral.nih.gov:10949144", "is_oa": true, "landing_page_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/10949144", "pdf_url": null, "source": {"id": "https://openalex.org/S2764455111", "display_name": "PubMed Central", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I1299303238", "host_organization_name": "National Institutes of Health", "host_organization_lineage": ["https://openalex.org/I1299303238"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "JAMA", "raw_type": "Text"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.46000000834465027, "display_name": "Quality Education"}], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 4, "referenced_works": ["https://openalex.org/W4361000349", "https://openalex.org/W4365143687", "https://openalex.org/W4385620111", "https://openalex.org/W4387744047"], "related_works": ["https://openalex.org/W2748952813", "https://openalex.org/W3031052312", "https://openalex.org/W4389568370", "https://openalex.org/W3032375762", "https://openalex.org/W1995515455", "https://openalex.org/W2080531066", "https://openalex.org/W604999504", "https://openalex.org/W3108674512", "https://openalex.org/W1506200166", "https://openalex.org/W582600639"], "abstract_inverted_index": {"This": [0], "study": [1], "compares": [2], "2": [3], "large": [4], "language": [5], "models": [6], "and": [7], "their": [8], "performance": [9], "vs": [10], "that": [11], "of": [12], "competing": [13], "open-source": [14], "models.": [15]}, "counts_by_year": [{"year": 2026, "cited_by_count": 17}, {"year": 2025, "cited_by_count": 37}, {"year": 2024, "cited_by_count": 23}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402727075", "doi": "https://doi.org/10.1109/cvpr52733.2024.01240", "title": "Sniffer: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection", "display_name": "Sniffer: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection", "relevance_score": 960.9967, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402727075", "doi": "https://doi.org/10.1109/cvpr52733.2024.01240"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.01240", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01240", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101682275", "display_name": "Peng Qi", "orcid": "https://orcid.org/0000-0001-7747-3293"}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}], "countries": ["SG"], "is_corresponding": true, "raw_author_name": "Peng Qi", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5002189012", "display_name": "Zehong Yan", "orcid": "https://orcid.org/0000-0002-0139-8917"}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Zehong Yan", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5051209739", "display_name": "Wynne Hsu", "orcid": "https://orcid.org/0000-0002-4142-8893"}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Wynne Hsu", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5019988958", "display_name": "Mong Li Lee", "orcid": "https://orcid.org/0000-0002-9636-388X"}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Mong Li Lee", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 4, "corresponding_author_ids": ["https://openalex.org/A5101682275"], "corresponding_institution_ids": ["https://openalex.org/I165932596"], "apc_list": null, "apc_paid": null, "fwci": 57.8604, "has_fulltext": false, "cited_by_count": 55, "citation_normalized_percentile": {"value": 0.999279, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 98, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "13052", "last_page": "13062"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9998999834060669, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9962000250816345, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9933000206947327, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/misinformation", "display_name": "Misinformation", "score": 0.7661093473434448}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.7587432265281677}, {"id": "https://openalex.org/keywords/context", "display_name": "Context (archaeology)", "score": 0.615967333316803}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.45535802841186523}, {"id": "https://openalex.org/keywords/context-model", "display_name": "Context model", "score": 0.4448869526386261}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.42195558547973633}, {"id": "https://openalex.org/keywords/computer-security", "display_name": "Computer security", "score": 0.11988586187362671}, {"id": "https://openalex.org/keywords/history", "display_name": "History", "score": 0.05597555637359619}], "concepts": [{"id": "https://openalex.org/C2776990098", "wikidata": "https://www.wikidata.org/wiki/Q13579947", "display_name": "Misinformation", "level": 2, "score": 0.7661093473434448}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.7587432265281677}, {"id": "https://openalex.org/C2779343474", "wikidata": "https://www.wikidata.org/wiki/Q3109175", "display_name": "Context (archaeology)", "level": 2, "score": 0.615967333316803}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.45535802841186523}, {"id": "https://openalex.org/C183322885", "wikidata": "https://www.wikidata.org/wiki/Q17007702", "display_name": "Context model", "level": 3, "score": 0.4448869526386261}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.42195558547973633}, {"id": "https://openalex.org/C38652104", "wikidata": "https://www.wikidata.org/wiki/Q3510521", "display_name": "Computer security", "level": 1, "score": 0.11988586187362671}, {"id": "https://openalex.org/C95457728", "wikidata": "https://www.wikidata.org/wiki/Q309", "display_name": "History", "level": 0, "score": 0.05597555637359619}, {"id": "https://openalex.org/C2781238097", "wikidata": "https://www.wikidata.org/wiki/Q175026", "display_name": "Object (grammar)", "level": 2, "score": 0.0}, {"id": "https://openalex.org/C166957645", "wikidata": "https://www.wikidata.org/wiki/Q23498", "display_name": "Archaeology", "level": 1, "score": 0.0}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.01240", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.01240", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/10", "score": 0.5199999809265137, "display_name": "Reduced inequalities"}], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 59, "referenced_works": ["https://openalex.org/W2768282280", "https://openalex.org/W2809476703", "https://openalex.org/W2888307497", "https://openalex.org/W2951307134", "https://openalex.org/W2968124245", "https://openalex.org/W2971291998", "https://openalex.org/W2982538645", "https://openalex.org/W3000155280", "https://openalex.org/W3003961771", "https://openalex.org/W3013743800", "https://openalex.org/W3022924198", "https://openalex.org/W3033767380", "https://openalex.org/W3038930935", "https://openalex.org/W3044534474", "https://openalex.org/W3105756487", "https://openalex.org/W3159012943", "https://openalex.org/W3195314408", "https://openalex.org/W3198760712", "https://openalex.org/W3206237685", "https://openalex.org/W3211405508", "https://openalex.org/W3215028386", "https://openalex.org/W4312655774", "https://openalex.org/W4366330503", "https://openalex.org/W4366342832", "https://openalex.org/W4366850747", "https://openalex.org/W4375869762", "https://openalex.org/W4376312115", "https://openalex.org/W4378465439", "https://openalex.org/W4379046666", "https://openalex.org/W4379259189", "https://openalex.org/W4382132560", "https://openalex.org/W4384648639", "https://openalex.org/W4385474632", "https://openalex.org/W4385572634", "https://openalex.org/W4386071472", "https://openalex.org/W4396816283", "https://openalex.org/W6740760497", "https://openalex.org/W6742165761", "https://openalex.org/W6746052068", "https://openalex.org/W6767279747", "https://openalex.org/W6778883912", "https://openalex.org/W6779317912", "https://openalex.org/W6791353385", "https://openalex.org/W6791449262", "https://openalex.org/W6794494545", "https://openalex.org/W6849177959", "https://openalex.org/W6849712728", "https://openalex.org/W6851592950", "https://openalex.org/W6851813333", "https://openalex.org/W6851950068", "https://openalex.org/W6852621682", "https://openalex.org/W6852989508", "https://openalex.org/W6853116092", "https://openalex.org/W6853444283", "https://openalex.org/W6853469104", "https://openalex.org/W6854308872", "https://openalex.org/W6855531725", "https://openalex.org/W6856148249", "https://openalex.org/W6856920807"], "related_works": ["https://openalex.org/W3204019825", "https://openalex.org/W2349222429", "https://openalex.org/W1993394192", "https://openalex.org/W3117430770", "https://openalex.org/W2116230991", "https://openalex.org/W2590751808", "https://openalex.org/W1972377868", "https://openalex.org/W2132709506", "https://openalex.org/W2186895195", "https://openalex.org/W2151995366"], "abstract_inverted_index": {"Misinformation": [0], "is": [1, 23], "a": [2], "prevalent": [3], "societal": [4], "issue": [5], "due": [6], "to": [7, 32, 144], "its": [8], "potential": [9], "high": [10], "risks.": [11], "Out-Of-Context": [12], "(OOC)": [13], "misinformation,": [14], "where": [15], "authentic": [16], "images": [17], "are": [18, 51], "repurposed": [19], "with": [20, 127], "false": [21], "text,": [22], "one": [24], "of": [25, 124], "the": [26, 84, 120, 131, 146, 180], "easiest": [27], "and": [28, 65, 72, 82, 107, 130, 155, 164, 186, 196, 204], "most": [29], "effective": [30], "ways": [31], "mislead": [33], "audiences.": [34], "Current": [35], "methods": [36, 189], "focus": [37], "on": [38, 113], "assessing": [39], "image-": [40], "text": [41, 163], "consistency": [42], "but": [43, 166], "lack": [44, 77], "convincing": [45], "explanations": [46, 198], "for": [47, 53, 68, 103, 171], "their": [48], "judgments,": [49], "which": [50], "essential": [52], "debunking": [54], "misinformation.": [55], "While": [56], "Multimodal": [57], "Large": [58], "Language": [59], "Models": [60], "(MLLMs)": [61], "have": [62], "rich": [63], "knowledge": [64, 170], "innate": [66], "capability": [67], "visual": [69], "rea-": [70], "soning": [71], "explanation": [73], "generation,": [74], "they": [75], "still": [76], "sophisti-": [78], "cation": [79], "in": [80, 190], "understanding": [81], "discovering": [83], "subtle": [85], "cross-": [86], "modal": [87], "differences.": [88], "In": [89], "this": [90], "paper,": [91], "we": [92], "introduce": [93], "Sniffer,a": [94], "novel": [95], "multimodal": [96], "large": [97], "language": [98], "model": [99], "specifically": [100], "engi-": [101], "neered": [102], "OOC": [104], "misinformation": [105], "detection": [106, 191], "explanation.": [108], "Snifferemploys": [109], "two-stage": [110], "instruction": [111, 137], "tuning": [112], "Instruct-": [114], "BLIP.": [115], "The": [116], "first": [117], "stage": [118, 134], "refines": [119], "model's": [121, 147], "concept": [122], "alignment": [123], "generic": [125], "objects": [126], "news-domain": [128], "entities": [129], "sec-": [132], "ond": [133], "leverages": [135], "OOC-specific": [136], "data": [138], "gener-": [139], "ated": [140], "by": [141, 152, 183, 202], "language-only": [142], "GPT-4": [143], "fine-tune": [145], "dis-": [148], "criminatory": [149], "powers.": [150], "Enhanced": [151], "external": [153, 169], "tools": [154], "re-": [156], "trieval,": [157], "Sniffernot": [158], "only": [159], "detects": [160], "inconsistencies": [161], "between": [162], "image": [165], "also": [167], "utilizes": [168], "con-": [172], "textual": [173], "verification.": [174], "Our": [175], "experiments": [176], "show": [177], "that": [178], "Sniffersurpasses": [179], "original": [181], "MLLM": [182], "over": [184], "40%": [185], "outperforms": [187], "state-of-the-art": [188], "accuracy.": [192], "Snifferalso": [193], "provides": [194], "accurate": [195], "persuasive": [197], "as": [199], "val-": [200], "idated": [201], "quantitative": [203], "human": [205], "evaluations.": [206]}, "counts_by_year": [{"year": 2026, "cited_by_count": 9}, {"year": 2025, "cited_by_count": 41}, {"year": 2024, "cited_by_count": 5}], "updated_date": "2026-05-08T15:41:06.802602", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402704633", "doi": "https://doi.org/10.1109/cvpr52733.2024.02553", "title": "Hallucination Augmented Contrastive Learning for Multimodal Large Language Model", "display_name": "Hallucination Augmented Contrastive Learning for Multimodal Large Language Model", "relevance_score": 916.1071, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402704633", "doi": "https://doi.org/10.1109/cvpr52733.2024.02553"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.02553", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.02553", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5062777592", "display_name": "Chaoya Jiang", "orcid": null}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Chaoya Jiang", "raw_affiliation_strings": ["National Engineering Research Center for Software Engineering, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Engineering Research Center for Software Engineering, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111023416", "display_name": "Haiyang Xu", "orcid": null}, "institutions": [{"id": "https://openalex.org/I4210095624", "display_name": "Alibaba Group (United States)", "ror": "https://ror.org/00rn0m335", "country_code": "US", "type": "company", "lineage": ["https://openalex.org/I4210095624", "https://openalex.org/I45928872"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Haiyang Xu", "raw_affiliation_strings": ["Alibaba Group"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Alibaba Group", "institution_ids": ["https://openalex.org/I4210095624"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111335368", "display_name": "Mengfan Dong", "orcid": "https://orcid.org/0009-0005-2526-9166"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Mengfan Dong", "raw_affiliation_strings": ["National Engineering Research Center for Software Engineering, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Engineering Research Center for Software Engineering, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100685932", "display_name": "Jiaxing Chen", "orcid": "https://orcid.org/0000-0001-7309-0535"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiaxing Chen", "raw_affiliation_strings": ["National Engineering Research Center for Software Engineering, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Engineering Research Center for Software Engineering, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101883632", "display_name": "Wei Ye", "orcid": "https://orcid.org/0009-0006-0568-9128"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wei Ye", "raw_affiliation_strings": ["National Engineering Research Center for Software Engineering, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Engineering Research Center for Software Engineering, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000844861", "display_name": "Ming Yan", "orcid": "https://orcid.org/0000-0002-4388-6708"}, "institutions": [{"id": "https://openalex.org/I4210095624", "display_name": "Alibaba Group (United States)", "ror": "https://ror.org/00rn0m335", "country_code": "US", "type": "company", "lineage": ["https://openalex.org/I4210095624", "https://openalex.org/I45928872"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ming Yan", "raw_affiliation_strings": ["Alibaba Group"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Alibaba Group", "institution_ids": ["https://openalex.org/I4210095624"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005965903", "display_name": "Qinghao Ye", "orcid": "https://orcid.org/0000-0002-7977-5540"}, "institutions": [{"id": "https://openalex.org/I4210095624", "display_name": "Alibaba Group (United States)", "ror": "https://ror.org/00rn0m335", "country_code": "US", "type": "company", "lineage": ["https://openalex.org/I4210095624", "https://openalex.org/I45928872"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Qinghao Ye", "raw_affiliation_strings": ["Alibaba Group"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Alibaba Group", "institution_ids": ["https://openalex.org/I4210095624"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100329282", "display_name": "Ji Zhang", "orcid": "https://orcid.org/0000-0003-3512-6589"}, "institutions": [{"id": "https://openalex.org/I4210095624", "display_name": "Alibaba Group (United States)", "ror": "https://ror.org/00rn0m335", "country_code": "US", "type": "company", "lineage": ["https://openalex.org/I4210095624", "https://openalex.org/I45928872"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ji Zhang", "raw_affiliation_strings": ["Alibaba Group"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Alibaba Group", "institution_ids": ["https://openalex.org/I4210095624"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101488344", "display_name": "Fei Huang", "orcid": "https://orcid.org/0000-0002-3709-5053"}, "institutions": [{"id": "https://openalex.org/I4210095624", "display_name": "Alibaba Group (United States)", "ror": "https://ror.org/00rn0m335", "country_code": "US", "type": "company", "lineage": ["https://openalex.org/I4210095624", "https://openalex.org/I45928872"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Fei Huang", "raw_affiliation_strings": ["Alibaba Group"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Alibaba Group", "institution_ids": ["https://openalex.org/I4210095624"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101435571", "display_name": "Shikun Zhang", "orcid": "https://orcid.org/0000-0002-8576-2674"}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shikun Zhang", "raw_affiliation_strings": ["National Engineering Research Center for Software Engineering, Peking University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Engineering Research Center for Software Engineering, Peking University", "institution_ids": ["https://openalex.org/I20231570"]}]}], "institutions": [], "countries_distinct_count": 2, "institutions_distinct_count": 10, "corresponding_author_ids": ["https://openalex.org/A5062777592"], "corresponding_institution_ids": ["https://openalex.org/I20231570"], "apc_list": null, "apc_paid": null, "fwci": 17.6973, "has_fulltext": false, "cited_by_count": 56, "citation_normalized_percentile": {"value": 0.99410893, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "27026", "last_page": "27036"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9919000267982483, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9919000267982483, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11273", "display_name": "Advanced Graph Neural Networks", "score": 0.9789000153541565, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9761000275611877, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.7068783640861511}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.48688021302223206}, {"id": "https://openalex.org/keywords/linguistics", "display_name": "Linguistics", "score": 0.4445101320743561}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.43601807951927185}, {"id": "https://openalex.org/keywords/philosophy", "display_name": "Philosophy", "score": 0.059015899896621704}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.7068783640861511}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.48688021302223206}, {"id": "https://openalex.org/C41895202", "wikidata": "https://www.wikidata.org/wiki/Q8162", "display_name": "Linguistics", "level": 1, "score": 0.4445101320743561}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.43601807951927185}, {"id": "https://openalex.org/C138885662", "wikidata": "https://www.wikidata.org/wiki/Q5891", "display_name": "Philosophy", "level": 0, "score": 0.059015899896621704}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.02553", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.02553", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.5299999713897705, "display_name": "Quality Education"}], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 80, "referenced_works": ["https://openalex.org/W1861492603", "https://openalex.org/W2842511635", "https://openalex.org/W2979382951", "https://openalex.org/W3004268082", "https://openalex.org/W3009561768", "https://openalex.org/W3035524453", "https://openalex.org/W3096609285", "https://openalex.org/W3129831491", "https://openalex.org/W3176641147", "https://openalex.org/W3184735396", "https://openalex.org/W3208314443", "https://openalex.org/W3214685499", "https://openalex.org/W4200268060", "https://openalex.org/W4224308101", "https://openalex.org/W4225323055", "https://openalex.org/W4283208789", "https://openalex.org/W4292779060", "https://openalex.org/W4297808394", "https://openalex.org/W4306820534", "https://openalex.org/W4312877428", "https://openalex.org/W4318718936", "https://openalex.org/W4322718191", "https://openalex.org/W4322718246", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4367628410", "https://openalex.org/W4375869762", "https://openalex.org/W4376122449", "https://openalex.org/W4376312115", "https://openalex.org/W4380353763", "https://openalex.org/W4382142077", "https://openalex.org/W4382323090", "https://openalex.org/W4382490555", "https://openalex.org/W4382491206", "https://openalex.org/W4382763281", "https://openalex.org/W4383604278", "https://openalex.org/W4384268538", "https://openalex.org/W4384918448", "https://openalex.org/W4385473806", "https://openalex.org/W4385572899", "https://openalex.org/W4385645323", "https://openalex.org/W4387436689", "https://openalex.org/W4387968057", "https://openalex.org/W4389519972", "https://openalex.org/W4389523832", "https://openalex.org/W4390874046", "https://openalex.org/W4393149022", "https://openalex.org/W4402670859", "https://openalex.org/W6774670964", "https://openalex.org/W6778883912", "https://openalex.org/W6791353385", "https://openalex.org/W6798805250", "https://openalex.org/W6804095316", "https://openalex.org/W6810081322", "https://openalex.org/W6810334672", "https://openalex.org/W6811013733", "https://openalex.org/W6839091850", "https://openalex.org/W6846007759", "https://openalex.org/W6849177959", "https://openalex.org/W6850015000", "https://openalex.org/W6850503672", "https://openalex.org/W6850625674", "https://openalex.org/W6851592950", "https://openalex.org/W6851813333", "https://openalex.org/W6851950068", "https://openalex.org/W6852060543", "https://openalex.org/W6852489829", "https://openalex.org/W6852667213", "https://openalex.org/W6853116092", "https://openalex.org/W6854222408", "https://openalex.org/W6854262950", "https://openalex.org/W6854308264", "https://openalex.org/W6854347851", "https://openalex.org/W6854510102", "https://openalex.org/W6854695065", "https://openalex.org/W6854866820", "https://openalex.org/W6855297460", "https://openalex.org/W6856535631", "https://openalex.org/W6857162426"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052", "https://openalex.org/W2382290278", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"Multi-modal": [0], "large": [1], "language": [2, 12], "models": [3], "(MLLMs)": [4], "have": [5], "been": [6], "shown": [7], "to": [8, 16, 32, 102, 116], "efficiently": [9], "integrate": [10], "natural": [11], "with": [13, 110, 129], "visual": [14, 62, 79, 142], "information": [15], "handle": [17], "multi-modal": [18], "tasks.": [19], "However,": [20], "MLLMs": [21, 45, 125], "still": [22], "face": [23], "a": [24, 47, 73, 111, 181], "fundamental": [25], "limitation": [26], "of": [27, 50, 59, 88, 138, 149], "hallucinations,": [28], "where": [29], "they": [30], "tend": [31], "generate": [33], "erroneous": [34], "or": [35], "fabricated": [36], "information.": [37], "In": [38], "this": [39], "paper,": [40], "we": [41, 120], "address": [42], "hallucinations": [43, 96], "in": [44, 64, 164], "from": [46], "novel": [48], "perspective": [49], "representation": [51, 57, 84], "learning.": [52], "We": [53, 154], "first": [54], "analyzed": [55], "the": [56, 175, 186], "distribution": [58], "textual": [60, 77], "and": [61, 78, 92, 126, 141, 151, 159, 168], "tokens": [63], "MLLM,": [65], "revealing": [66], "two": [67, 106], "important": [68], "findings:": [69], "1)": [70], "there": [71], "is": [72, 191], "significant": [74], "gap": [75], "between": [76], "representations,": [80], "indicating": [81], "unsatisfactory": [82], "cross-modal": [83], "alignment;": [85], "2)": [86], "representations": [87, 137, 148], "texts": [89], "that": [90], "contain": [91, 95], "do": [93], "not": [94], "are": [97], "entangled,": [98], "making": [99], "it": [100], "challenging": [101], "distinguish": [103], "them.": [104], "These": [105], "observations": [107], "inspire": [108], "us": [109], "simple": [112], "yet": [113], "effective": [114], "method": [115, 157, 179], "mitigate": [117], "hallucinations.": [118], "Specifically,": [119], "introduce": [121], "contrastive": [122], "learning": [123], "into": [124], "use": [127], "text": [128, 140], "hallucination": [130, 166], "as": [131], "hard": [132], "negative": [133], "examples,": [134], "naturally": [135], "bringing": [136], "non-hallucinative": [139], "samples": [143], "closer": [144], "while": [145], "pushing": [146], "way": [147], "non-hallucinating": [150], "hallucinative": [152], "text.": [153], "evaluate": [155], "our": [156, 178], "quantitatively": [158], "qualitatively,": [160], "showing": [161], "its": [162], "effectiveness": [163], "reducing": [165], "occurrences": [167], "improving": [169], "performance": [170], "across": [171], "multiple": [172], "benchmarks.": [173], "On": [174], "MMhal-Bench": [176], "benchmark,": [177], "obtains": [180], "34.66%": [182], "/29.5%": [183], "improvement": [184], "over": [185], "baseline": [187], "MiniGPT-4/LLaVA.": [188], "Our": [189], "code": [190], "available": [192], "on": [193], "https://github.com/X-PLUG/mPLUG-HalOwl/tree/main/hacl.": [194]}, "counts_by_year": [{"year": 2026, "cited_by_count": 9}, {"year": 2025, "cited_by_count": 37}, {"year": 2024, "cited_by_count": 10}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4402727124", "doi": "https://doi.org/10.1109/cvpr52733.2024.00370", "title": "GSVA: Generalized Segmentation via Multimodal Large Language Models", "display_name": "GSVA: Generalized Segmentation via Multimodal Large Language Models", "relevance_score": 894.28125, "publication_year": 2024, "publication_date": "2024-06-16", "ids": {"openalex": "https://openalex.org/W4402727124", "doi": "https://doi.org/10.1109/cvpr52733.2024.00370"}, "language": "en", "primary_location": {"id": "doi:10.1109/cvpr52733.2024.00370", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.00370", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": false, "oa_status": "closed", "oa_url": null, "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102797436", "display_name": "Zhuofan Xia", "orcid": "https://orcid.org/0009-0001-7965-364X"}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Zhuofan Xia", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102210006", "display_name": "Dongchen Han", "orcid": null}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Dongchen Han", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5045569962", "display_name": "Yizeng Han", "orcid": "https://orcid.org/0000-0001-5706-8784"}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yizeng Han", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101086461", "display_name": "Xuran Pan", "orcid": null}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xuran Pan", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101868177", "display_name": "Shiji Song", "orcid": "https://orcid.org/0000-0002-4258-5217"}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shiji Song", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5013240918", "display_name": "Gao Huang", "orcid": "https://orcid.org/0000-0002-7251-0988"}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Gao Huang", "raw_affiliation_strings": ["Department of Automation, BNRist, Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, BNRist, Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 6, "corresponding_author_ids": ["https://openalex.org/A5102797436"], "corresponding_institution_ids": ["https://openalex.org/I99065089"], "apc_list": null, "apc_paid": null, "fwci": 9.7692, "has_fulltext": false, "cited_by_count": 42, "citation_normalized_percentile": {"value": 0.98805897, "is_in_top_1_percent": false, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 98, "max": 100}, "biblio": {"volume": null, "issue": null, "first_page": "3858", "last_page": "3869"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9998000264167786, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.9997000098228455, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9995999932289124, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.6795276999473572}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.5029603838920593}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.49216121435165405}, {"id": "https://openalex.org/keywords/segmentation", "display_name": "Segmentation", "score": 0.47905218601226807}], "concepts": [{"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.6795276999473572}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.5029603838920593}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.49216121435165405}, {"id": "https://openalex.org/C89600930", "wikidata": "https://www.wikidata.org/wiki/Q1423946", "display_name": "Segmentation", "level": 2, "score": 0.47905218601226807}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.1109/cvpr52733.2024.00370", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/cvpr52733.2024.00370", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "raw_type": "proceedings-article"}], "best_oa_location": null, "sustainable_development_goals": [], "awards": [], "funders": [], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 138, "referenced_works": ["https://openalex.org/W2065749455", "https://openalex.org/W2251512949", "https://openalex.org/W2302548814", "https://openalex.org/W2489434015", "https://openalex.org/W2605127024", "https://openalex.org/W2798556392", "https://openalex.org/W2894964039", "https://openalex.org/W2963109634", "https://openalex.org/W2964345792", "https://openalex.org/W2964935470", "https://openalex.org/W2967186499", "https://openalex.org/W2980088508", "https://openalex.org/W3004019157", "https://openalex.org/W3034578524", "https://openalex.org/W3035097537", "https://openalex.org/W3094502228", "https://openalex.org/W3166396011", "https://openalex.org/W3167976421", "https://openalex.org/W3169884222", "https://openalex.org/W3172522282", "https://openalex.org/W3187664142", "https://openalex.org/W3197501724", "https://openalex.org/W3201770677", "https://openalex.org/W3204647170", "https://openalex.org/W3211681816", "https://openalex.org/W3211783547", "https://openalex.org/W3216551675", "https://openalex.org/W4200631575", "https://openalex.org/W4214661601", "https://openalex.org/W4225323055", "https://openalex.org/W4226146163", "https://openalex.org/W4226224676", "https://openalex.org/W4226278401", "https://openalex.org/W4226334005", "https://openalex.org/W4290714341", "https://openalex.org/W4292779060", "https://openalex.org/W4307079201", "https://openalex.org/W4310825192", "https://openalex.org/W4312253723", "https://openalex.org/W4312429345", "https://openalex.org/W4312960790", "https://openalex.org/W4313483544", "https://openalex.org/W4318718936", "https://openalex.org/W4319994481", "https://openalex.org/W4322718191", "https://openalex.org/W4324128075", "https://openalex.org/W4361229539", "https://openalex.org/W4365606129", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4376312115", "https://openalex.org/W4377164404", "https://openalex.org/W4380137118", "https://openalex.org/W4382490555", "https://openalex.org/W4383109113", "https://openalex.org/W4384648427", "https://openalex.org/W4384918448", "https://openalex.org/W4385890358", "https://openalex.org/W4385958573", "https://openalex.org/W4386066126", "https://openalex.org/W4386071687", "https://openalex.org/W4386075493", "https://openalex.org/W4386075796", "https://openalex.org/W4386076142", "https://openalex.org/W4386076522", "https://openalex.org/W4386556626", "https://openalex.org/W4386794522", "https://openalex.org/W4386942429", "https://openalex.org/W4388160373", "https://openalex.org/W4388482029", "https://openalex.org/W4388555629", "https://openalex.org/W4388585422", "https://openalex.org/W4388685775", "https://openalex.org/W4389760959", "https://openalex.org/W4390048747", "https://openalex.org/W4390871961", "https://openalex.org/W4390872066", "https://openalex.org/W4390873528", "https://openalex.org/W4390874388", "https://openalex.org/W4390874500", "https://openalex.org/W4395481535", "https://openalex.org/W4402660140", "https://openalex.org/W4402703023", "https://openalex.org/W4402727018", "https://openalex.org/W4402727815", "https://openalex.org/W4402779867", "https://openalex.org/W6697921835", "https://openalex.org/W6755525882", "https://openalex.org/W6761275059", "https://openalex.org/W6773752455", "https://openalex.org/W6778883912", "https://openalex.org/W6784333009", "https://openalex.org/W6790299800", "https://openalex.org/W6791353385", "https://openalex.org/W6794072352", "https://openalex.org/W6801511446", "https://openalex.org/W6802996638", "https://openalex.org/W6810334672", "https://openalex.org/W6810738896", "https://openalex.org/W6845853401", "https://openalex.org/W6846474340", "https://openalex.org/W6847592527", "https://openalex.org/W6848909144", "https://openalex.org/W6849177959", "https://openalex.org/W6849977910", "https://openalex.org/W6850147914", "https://openalex.org/W6850410108", "https://openalex.org/W6850625674", "https://openalex.org/W6850787431", "https://openalex.org/W6851578965", "https://openalex.org/W6851592950", "https://openalex.org/W6851607685", "https://openalex.org/W6851948999", "https://openalex.org/W6851950068", "https://openalex.org/W6852060543", "https://openalex.org/W6852999659", "https://openalex.org/W6853105247", "https://openalex.org/W6853116092", "https://openalex.org/W6853875005", "https://openalex.org/W6854222408", "https://openalex.org/W6854596735", "https://openalex.org/W6854866820", "https://openalex.org/W6856032414", "https://openalex.org/W6856153088", "https://openalex.org/W6856194933", "https://openalex.org/W6856224812", "https://openalex.org/W6856329738", "https://openalex.org/W6856418075", "https://openalex.org/W6856984412", "https://openalex.org/W6857986322", "https://openalex.org/W6858029246", "https://openalex.org/W6858202685", "https://openalex.org/W6858268588", "https://openalex.org/W6858380932", "https://openalex.org/W6858938727", "https://openalex.org/W6859189955", "https://openalex.org/W6859799704"], "related_works": ["https://openalex.org/W4391375266", "https://openalex.org/W2748952813", "https://openalex.org/W2390279801", "https://openalex.org/W2358668433", "https://openalex.org/W4396701345", "https://openalex.org/W2376932109", "https://openalex.org/W2001405890", "https://openalex.org/W4396696052", "https://openalex.org/W2382290278", "https://openalex.org/W3204019825"], "abstract_inverted_index": {"Generalized": [0, 144], "Referring": [1], "Expression": [2], "Segmentation": [3, 145], "(GRES)": [4], "extends": [5], "the": [6, 21, 26, 33, 38, 41, 102, 119, 156, 161, 180, 190, 203], "scope": [7], "of": [8, 37], "classic": [9, 214], "RES": [10, 103], "to": [11, 13, 90, 98, 108, 149, 159, 173, 178], "refer": [12], "multiple": [14, 125, 166], "ob-jects": [15], "in": [16, 25, 31, 40, 57, 73, 101, 127, 188], "one": [17], "expression": [18], "or": [19, 131], "identify": [20], "empty": [22], "targets": [23, 182], "absent": [24], "image.": [27], "GRES": [28, 109, 191, 204], "poses": [29], "challenges": [30], "modeling": [32], "com-plex": [34], "spatial": [35], "relationships": [36], "instances": [39], "image": [42, 137], "and": [43, 67, 170, 197, 217], "identifying": [44], "non-existing": [45], "referents.": [46], "Multimodal": [47], "Large": [48, 63], "Language": [49, 64], "Models": [50, 65], "(MLLMs)": [51], "have": [52], "recently": [53], "shown": [54], "tremendous": [55], "progress": [56], "these": [58], "complicated": [59], "vision-language": [60], "tasks.": [61, 219], "Con-necting": [62], "(LLMs)": [66], "vision": [68], "models,": [69], "MLLMs": [70, 100, 115], "are": [71], "proficient": [72], "understanding": [74], "contexts": [75], "with": [76, 135], "visual": [77], "inputs.": [78], "Among": [79], "them,": [80], "LISA,": [81], "as": [82], "a": [83, 86, 92, 128, 175, 194, 199], "representative,": [84], "adopts": [85], "special": [87], "[SEG]": [88, 157], "token": [89, 158, 177], "prompt": [91, 130, 160], "segmentation": [93, 114, 162], "mask": [94, 167], "de-coder,": [95], "e.g.,": [96], "SAM,": [97], "enable": [99], "task.": [104], "How-ever,": [105], "existing": [106], "solutions": [107], "remain": [110], "unsatisfactory": [111], "since": [112], "current": [113], "cannot": [116], "correctly": [117], "handle": [118], "cases": [120], "where": [121], "users": [122], "might": [123], "reference": [124], "subjects": [126], "singular": [129], "provide": [132], "descriptions": [133], "incongruent": [134], "any": [136], "target.": [138], "In": [139], "this": [140, 151], "paper,": [141], "we": [142], "propose": [143], "Vision": [146], "Assistant": [147], "(GSVA)": [148], "address": [150], "gap.": [152], "Specifically,": [153], "GSVA": [154, 208], "reuses": [155], "model": [163], "towards": [164], "supporting": [165], "ref-erences": [168], "simultaneously": [169], "innovatively": [171], "learns": [172], "generate": [174], "[REJ]": [176], "reject": [179], "null": [181], "explicitly.": [183], "Ex-periments": [184], "validate": [185], "GSVA's": [186], "efficacy": [187], "resolving": [189], "issue,": [192], "marking": [193], "notable": [195], "enhancement": [196], "setting": [198], "new": [200], "record": [201], "on": [202], "benchmark": [205], "gRefCOCO": [206], "dataset.": [207], "also": [209], "proves": [210], "effective": [211], "across": [212], "various": [213], "referring": [215], "seg-mentation": [216], "comprehension": [218], "Code": [220], "is": [221], "available": [222], "at": [223], "https://github.com/LeapLabTHU/GSVA.": [224]}, "counts_by_year": [{"year": 2026, "cited_by_count": 7}, {"year": 2025, "cited_by_count": 29}, {"year": 2024, "cited_by_count": 6}], "updated_date": "2026-05-05T08:41:31.759640", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4406232026", "doi": "https://doi.org/10.1016/j.lindif.2024.102601", "title": "Taking the next step with generative artificial intelligence: The transformative role of multimodal large language models in science education", "display_name": "Taking the next step with generative artificial intelligence: The transformative role of multimodal large language models in science education", "relevance_score": 885.4408, "publication_year": 2025, "publication_date": "2025-01-09", "ids": {"openalex": "https://openalex.org/W4406232026", "doi": "https://doi.org/10.1016/j.lindif.2024.102601"}, "language": "en", "primary_location": {"id": "doi:10.1016/j.lindif.2024.102601", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.lindif.2024.102601", "pdf_url": null, "source": {"id": "https://openalex.org/S9267903", "display_name": "Learning and Individual Differences", "issn_l": "1041-6080", "issn": ["1041-6080", "1873-3425"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Learning and Individual Differences", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": true, "oa_status": "hybrid", "oa_url": "https://doi.org/10.1016/j.lindif.2024.102601", "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5015478550", "display_name": "Arne Bewersdorff", "orcid": "https://orcid.org/0000-0002-9725-268X"}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Arne Bewersdorff", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044685738", "display_name": "Christian Hartmann", "orcid": "https://orcid.org/0000-0003-3109-1104"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Christian Hartmann", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000415562", "display_name": "Marie Hornberger", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Marie Hornberger", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5013346660", "display_name": "Kathrin Se\u00dfler", "orcid": "https://orcid.org/0000-0002-3380-4641"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kathrin Se\u00dfler", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052257833", "display_name": "Maria Bannert", "orcid": "https://orcid.org/0000-0001-7045-2764"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Maria Bannert", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5008809634", "display_name": "Enkelejda Kasneci", "orcid": "https://orcid.org/0000-0003-3146-4484"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Enkelejda Kasneci", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024434748", "display_name": "Gjergji Kasneci", "orcid": null}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gjergji Kasneci", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5013379229", "display_name": "Xiaoming Zha\u0131", "orcid": "https://orcid.org/0000-0003-4519-1931"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xiaoming Zhai", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5063270174", "display_name": "Claudia Nerdel", "orcid": "https://orcid.org/0000-0003-1170-8875"}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Claudia Nerdel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "institutions": [], "countries_distinct_count": 0, "institutions_distinct_count": 9, "corresponding_author_ids": ["https://openalex.org/A5015478550"], "corresponding_institution_ids": [], "apc_list": {"value": 3430, "currency": "USD", "value_usd": 3430}, "apc_paid": {"value": 3430, "currency": "USD", "value_usd": 3430}, "fwci": 233.2333, "has_fulltext": false, "cited_by_count": 91, "citation_normalized_percentile": {"value": 1.0, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 96, "max": 100}, "biblio": {"volume": "118", "issue": null, "first_page": "102601", "last_page": "102601"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10636", "display_name": "Innovative Teaching and Learning Methods", "score": 0.9901999831199646, "subfield": {"id": "https://openalex.org/subfields/3204", "display_name": "Developmental and Educational Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T10636", "display_name": "Innovative Teaching and Learning Methods", "score": 0.9901999831199646, "subfield": {"id": "https://openalex.org/subfields/3204", "display_name": "Developmental and Educational Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10731", "display_name": "Educational Games and Gamification", "score": 0.9883000254631042, "subfield": {"id": "https://openalex.org/subfields/3204", "display_name": "Developmental and Educational Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11516", "display_name": "Visual and Cognitive Learning Processes", "score": 0.9796000123023987, "subfield": {"id": "https://openalex.org/subfields/3205", "display_name": "Experimental and Cognitive Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/transformative-learning", "display_name": "Transformative learning", "score": 0.9269542694091797}, {"id": "https://openalex.org/keywords/generative-grammar", "display_name": "Generative grammar", "score": 0.8132421970367432}, {"id": "https://openalex.org/keywords/psychology", "display_name": "Psychology", "score": 0.7172099947929382}, {"id": "https://openalex.org/keywords/cognitive-science", "display_name": "Cognitive science", "score": 0.5104026198387146}, {"id": "https://openalex.org/keywords/generative-model", "display_name": "Generative model", "score": 0.4720264971256256}, {"id": "https://openalex.org/keywords/language-acquisition", "display_name": "Language acquisition", "score": 0.43188437819480896}, {"id": "https://openalex.org/keywords/cognitive-psychology", "display_name": "Cognitive psychology", "score": 0.34242701530456543}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.25219374895095825}, {"id": "https://openalex.org/keywords/mathematics-education", "display_name": "Mathematics education", "score": 0.20091310143470764}, {"id": "https://openalex.org/keywords/pedagogy", "display_name": "Pedagogy", "score": 0.18474119901657104}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.1555970013141632}], "concepts": [{"id": "https://openalex.org/C70587473", "wikidata": "https://www.wikidata.org/wiki/Q7834111", "display_name": "Transformative learning", "level": 2, "score": 0.9269542694091797}, {"id": "https://openalex.org/C39890363", "wikidata": "https://www.wikidata.org/wiki/Q36108", "display_name": "Generative grammar", "level": 2, "score": 0.8132421970367432}, {"id": "https://openalex.org/C15744967", "wikidata": "https://www.wikidata.org/wiki/Q9418", "display_name": "Psychology", "level": 0, "score": 0.7172099947929382}, {"id": "https://openalex.org/C188147891", "wikidata": "https://www.wikidata.org/wiki/Q147638", "display_name": "Cognitive science", "level": 1, "score": 0.5104026198387146}, {"id": "https://openalex.org/C167966045", "wikidata": "https://www.wikidata.org/wiki/Q5532625", "display_name": "Generative model", "level": 3, "score": 0.4720264971256256}, {"id": "https://openalex.org/C74672266", "wikidata": "https://www.wikidata.org/wiki/Q815859", "display_name": "Language acquisition", "level": 2, "score": 0.43188437819480896}, {"id": "https://openalex.org/C180747234", "wikidata": "https://www.wikidata.org/wiki/Q23373", "display_name": "Cognitive psychology", "level": 1, "score": 0.34242701530456543}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.25219374895095825}, {"id": "https://openalex.org/C145420912", "wikidata": "https://www.wikidata.org/wiki/Q853077", "display_name": "Mathematics education", "level": 1, "score": 0.20091310143470764}, {"id": "https://openalex.org/C19417346", "wikidata": "https://www.wikidata.org/wiki/Q7922", "display_name": "Pedagogy", "level": 1, "score": 0.18474119901657104}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.1555970013141632}], "mesh": [], "locations_count": 2, "locations": [{"id": "doi:10.1016/j.lindif.2024.102601", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.lindif.2024.102601", "pdf_url": null, "source": {"id": "https://openalex.org/S9267903", "display_name": "Learning and Individual Differences", "issn_l": "1041-6080", "issn": ["1041-6080", "1873-3425"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Learning and Individual Differences", "raw_type": "journal-article"}, {"id": "pmh:oai:mediatum.ub.tum.de:node/1768072", "is_oa": false, "landing_page_url": "https://mediatum.ub.tum.de/1768072", "pdf_url": null, "source": {"id": "https://openalex.org/S4377196330", "display_name": "mediaTUM  (Technical University of Munich)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "host_organization": "https://openalex.org/I62916508", "host_organization_name": "Technical University of Munich", "host_organization_lineage": ["https://openalex.org/I62916508"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "article"}], "best_oa_location": {"id": "doi:10.1016/j.lindif.2024.102601", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.lindif.2024.102601", "pdf_url": null, "source": {"id": "https://openalex.org/S9267903", "display_name": "Learning and Individual Differences", "issn_l": "1041-6080", "issn": ["1041-6080", "1873-3425"], "is_oa": false, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Learning and Individual Differences", "raw_type": "journal-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/4", "score": 0.5699999928474426, "display_name": "Quality Education"}], "awards": [], "funders": [{"id": "https://openalex.org/F4320306076", "display_name": "National Science Foundation", "ror": "https://ror.org/021nxhr62"}], "has_content": {"pdf": false, "grobid_xml": false}, "content_urls": null, "referenced_works_count": 113, "referenced_works": ["https://openalex.org/W101460816", "https://openalex.org/W352610149", "https://openalex.org/W1544649311", "https://openalex.org/W1849208916", "https://openalex.org/W1976637107", "https://openalex.org/W1985953330", "https://openalex.org/W1989877703", "https://openalex.org/W2032926804", "https://openalex.org/W2033011208", "https://openalex.org/W2045795773", "https://openalex.org/W2051453100", "https://openalex.org/W2055556052", "https://openalex.org/W2057453755", "https://openalex.org/W2058077812", "https://openalex.org/W2058817143", "https://openalex.org/W2062630085", "https://openalex.org/W2067983851", "https://openalex.org/W2080316367", "https://openalex.org/W2090334926", "https://openalex.org/W2103857331", "https://openalex.org/W2105477144", "https://openalex.org/W2110661236", "https://openalex.org/W2126153334", "https://openalex.org/W2158764547", "https://openalex.org/W2164185374", "https://openalex.org/W2213284889", "https://openalex.org/W2313328299", "https://openalex.org/W2501209931", "https://openalex.org/W2560140854", "https://openalex.org/W2886409168", "https://openalex.org/W2907492528", "https://openalex.org/W2947850794", "https://openalex.org/W2960603406", "https://openalex.org/W2980142878", "https://openalex.org/W2991192916", "https://openalex.org/W3025708509", "https://openalex.org/W3036079157", "https://openalex.org/W3048335295", "https://openalex.org/W3195577433", "https://openalex.org/W3197048544", "https://openalex.org/W3202428668", "https://openalex.org/W4224308101", "https://openalex.org/W4225323055", "https://openalex.org/W4226278401", "https://openalex.org/W4230938361", "https://openalex.org/W4250995094", "https://openalex.org/W4256016184", "https://openalex.org/W4285255124", "https://openalex.org/W4291476001", "https://openalex.org/W4292779060", "https://openalex.org/W4297183894", "https://openalex.org/W4306178203", "https://openalex.org/W4308521188", "https://openalex.org/W4309674289", "https://openalex.org/W4313678819", "https://openalex.org/W4318014888", "https://openalex.org/W4319165821", "https://openalex.org/W4322718191", "https://openalex.org/W4323572061", "https://openalex.org/W4323717348", "https://openalex.org/W4353015365", "https://openalex.org/W4361866031", "https://openalex.org/W4366330503", "https://openalex.org/W4366850747", "https://openalex.org/W4367367040", "https://openalex.org/W4375958083", "https://openalex.org/W4376167553", "https://openalex.org/W4378188087", "https://openalex.org/W4378711593", "https://openalex.org/W4379468930", "https://openalex.org/W4380353763", "https://openalex.org/W4381930693", "https://openalex.org/W4382656966", "https://openalex.org/W4384918448", "https://openalex.org/W4384920109", "https://openalex.org/W4385572162", "https://openalex.org/W4386081431", "https://openalex.org/W4386261929", "https://openalex.org/W4386265233", "https://openalex.org/W4386401584", "https://openalex.org/W4386570516", "https://openalex.org/W4386655647", "https://openalex.org/W4387824566", "https://openalex.org/W4388964570", "https://openalex.org/W4389524500", "https://openalex.org/W4389713681", "https://openalex.org/W4389727268", "https://openalex.org/W4389983813", "https://openalex.org/W4389991855", "https://openalex.org/W4390954073", "https://openalex.org/W4391559941", "https://openalex.org/W4393178509", "https://openalex.org/W4396816283", "https://openalex.org/W4402671548", "https://openalex.org/W4403637324", "https://openalex.org/W6603944418", "https://openalex.org/W6609206729", "https://openalex.org/W6650843822", "https://openalex.org/W6670467450", "https://openalex.org/W6691703994", "https://openalex.org/W6773280460", "https://openalex.org/W6778369530", "https://openalex.org/W6781544461", "https://openalex.org/W6797362744", "https://openalex.org/W6801744293", "https://openalex.org/W6809908440", "https://openalex.org/W6810595431", "https://openalex.org/W6852811793", "https://openalex.org/W6855673737", "https://openalex.org/W6856886064", "https://openalex.org/W6857685708", "https://openalex.org/W6859368185", "https://openalex.org/W6860198022"], "related_works": ["https://openalex.org/W2326080043", "https://openalex.org/W4365211920", "https://openalex.org/W3014948380", "https://openalex.org/W4391584540", "https://openalex.org/W4380551139", "https://openalex.org/W4317695495", "https://openalex.org/W4395044357", "https://openalex.org/W4287117424", "https://openalex.org/W4387506531", "https://openalex.org/W2087346071"], "abstract_inverted_index": null, "counts_by_year": [{"year": 2026, "cited_by_count": 33}, {"year": 2025, "cited_by_count": 55}, {"year": 2024, "cited_by_count": 3}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}, {"id": "https://openalex.org/W4405317693", "doi": "https://doi.org/10.3390/electronics13244912", "title": "Multimodal Large Language Model-Based Fault Detection and Diagnosis in Context of Industry 4.0", "display_name": "Multimodal Large Language Model-Based Fault Detection and Diagnosis in Context of Industry 4.0", "relevance_score": 853.8879, "publication_year": 2024, "publication_date": "2024-12-12", "ids": {"openalex": "https://openalex.org/W4405317693", "doi": "https://doi.org/10.3390/electronics13244912"}, "language": "en", "primary_location": {"id": "doi:10.3390/electronics13244912", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/electronics13244912", "pdf_url": "https://www.mdpi.com/2079-9292/13/24/4912/pdf?version=1734017112", "source": {"id": "https://openalex.org/S4210202905", "display_name": "Electronics", "issn_l": "2079-9292", "issn": ["2079-9292"], "is_oa": true, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Electronics", "raw_type": "journal-article"}, "type": "article", "indexed_in": ["crossref"], "open_access": {"is_oa": true, "oa_status": "gold", "oa_url": "https://www.mdpi.com/2079-9292/13/24/4912/pdf?version=1734017112", "any_repository_has_fulltext": false}, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5020574558", "display_name": "Khalid Alsaif", "orcid": "https://orcid.org/0000-0001-5082-441X"}, "institutions": [{"id": "https://openalex.org/I185163786", "display_name": "King Abdulaziz University", "ror": "https://ror.org/02ma4wv74", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I185163786"]}], "countries": ["SA"], "is_corresponding": true, "raw_author_name": "Khalid M. Alsaif", "raw_affiliation_strings": ["Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0001-5082-441X", "affiliations": [{"raw_affiliation_string": "Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia", "institution_ids": ["https://openalex.org/I185163786"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5045587553", "display_name": "Aiiad Albeshri", "orcid": "https://orcid.org/0000-0003-3796-0294"}, "institutions": [{"id": "https://openalex.org/I185163786", "display_name": "King Abdulaziz University", "ror": "https://ror.org/02ma4wv74", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I185163786"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Aiiad A. Albeshri", "raw_affiliation_strings": ["Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0003-3796-0294", "affiliations": [{"raw_affiliation_string": "Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia", "institution_ids": ["https://openalex.org/I185163786"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019492006", "display_name": "Maher Khemakhem", "orcid": "https://orcid.org/0000-0002-1287-1634"}, "institutions": [{"id": "https://openalex.org/I185163786", "display_name": "King Abdulaziz University", "ror": "https://ror.org/02ma4wv74", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I185163786"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Maher A. Khemakhem", "raw_affiliation_strings": ["Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia"], "raw_orcid": "https://orcid.org/0000-0002-1287-1634", "affiliations": [{"raw_affiliation_string": "Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia", "institution_ids": ["https://openalex.org/I185163786"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5025984879", "display_name": "Fathy Eassa", "orcid": "https://orcid.org/0000-0003-3987-9051"}, "institutions": [{"id": "https://openalex.org/I185163786", "display_name": "King Abdulaziz University", "ror": "https://ror.org/02ma4wv74", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I185163786"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Fathy E. Eassa", "raw_affiliation_strings": ["Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia", "institution_ids": ["https://openalex.org/I185163786"]}]}], "institutions": [], "countries_distinct_count": 1, "institutions_distinct_count": 4, "corresponding_author_ids": ["https://openalex.org/A5020574558"], "corresponding_institution_ids": ["https://openalex.org/I185163786"], "apc_list": {"value": 2000, "currency": "CHF", "value_usd": 2165}, "apc_paid": {"value": 2000, "currency": "CHF", "value_usd": 2165}, "fwci": 14.1587, "has_fulltext": true, "cited_by_count": 47, "citation_normalized_percentile": {"value": 0.99404762, "is_in_top_1_percent": true, "is_in_top_10_percent": true}, "cited_by_percentile_year": {"min": 99, "max": 100}, "biblio": {"volume": "13", "issue": "24", "first_page": "4912", "last_page": "4912"}, "is_retracted": false, "is_paratext": false, "is_xpac": false, "primary_topic": {"id": "https://openalex.org/T10876", "display_name": "Fault Detection and Control Systems", "score": 0.9969000220298767, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10876", "display_name": "Fault Detection and Control Systems", "score": 0.9969000220298767, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10220", "display_name": "Machine Fault Diagnosis Techniques", "score": 0.9836999773979187, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11357", "display_name": "Risk and Safety Analysis", "score": 0.9765999913215637, "subfield": {"id": "https://openalex.org/subfields/1804", "display_name": "Statistics, Probability and Uncertainty"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "keywords": [{"id": "https://openalex.org/keywords/context", "display_name": "Context (archaeology)", "score": 0.652539849281311}, {"id": "https://openalex.org/keywords/computer-science", "display_name": "Computer science", "score": 0.5629159808158875}, {"id": "https://openalex.org/keywords/fault-detection-and-isolation", "display_name": "Fault detection and isolation", "score": 0.554810643196106}, {"id": "https://openalex.org/keywords/fault", "display_name": "Fault (geology)", "score": 0.5286532044410706}, {"id": "https://openalex.org/keywords/artificial-intelligence", "display_name": "Artificial intelligence", "score": 0.3522690534591675}, {"id": "https://openalex.org/keywords/natural-language-processing", "display_name": "Natural language processing", "score": 0.33917880058288574}, {"id": "https://openalex.org/keywords/real-time-computing", "display_name": "Real-time computing", "score": 0.33113813400268555}, {"id": "https://openalex.org/keywords/reliability-engineering", "display_name": "Reliability engineering", "score": 0.32621002197265625}, {"id": "https://openalex.org/keywords/software-engineering", "display_name": "Software engineering", "score": 0.3222905695438385}, {"id": "https://openalex.org/keywords/engineering", "display_name": "Engineering", "score": 0.2995380163192749}, {"id": "https://openalex.org/keywords/seismology", "display_name": "Seismology", "score": 0.10464358329772949}, {"id": "https://openalex.org/keywords/geography", "display_name": "Geography", "score": 0.08632615208625793}, {"id": "https://openalex.org/keywords/geology", "display_name": "Geology", "score": 0.06977018713951111}], "concepts": [{"id": "https://openalex.org/C2779343474", "wikidata": "https://www.wikidata.org/wiki/Q3109175", "display_name": "Context (archaeology)", "level": 2, "score": 0.652539849281311}, {"id": "https://openalex.org/C41008148", "wikidata": "https://www.wikidata.org/wiki/Q21198", "display_name": "Computer science", "level": 0, "score": 0.5629159808158875}, {"id": "https://openalex.org/C152745839", "wikidata": "https://www.wikidata.org/wiki/Q5438153", "display_name": "Fault detection and isolation", "level": 3, "score": 0.554810643196106}, {"id": "https://openalex.org/C175551986", "wikidata": "https://www.wikidata.org/wiki/Q47089", "display_name": "Fault (geology)", "level": 2, "score": 0.5286532044410706}, {"id": "https://openalex.org/C154945302", "wikidata": "https://www.wikidata.org/wiki/Q11660", "display_name": "Artificial intelligence", "level": 1, "score": 0.3522690534591675}, {"id": "https://openalex.org/C204321447", "wikidata": "https://www.wikidata.org/wiki/Q30642", "display_name": "Natural language processing", "level": 1, "score": 0.33917880058288574}, {"id": "https://openalex.org/C79403827", "wikidata": "https://www.wikidata.org/wiki/Q3988", "display_name": "Real-time computing", "level": 1, "score": 0.33113813400268555}, {"id": "https://openalex.org/C200601418", "wikidata": "https://www.wikidata.org/wiki/Q2193887", "display_name": "Reliability engineering", "level": 1, "score": 0.32621002197265625}, {"id": "https://openalex.org/C115903868", "wikidata": "https://www.wikidata.org/wiki/Q80993", "display_name": "Software engineering", "level": 1, "score": 0.3222905695438385}, {"id": "https://openalex.org/C127413603", "wikidata": "https://www.wikidata.org/wiki/Q11023", "display_name": "Engineering", "level": 0, "score": 0.2995380163192749}, {"id": "https://openalex.org/C165205528", "wikidata": "https://www.wikidata.org/wiki/Q83371", "display_name": "Seismology", "level": 1, "score": 0.10464358329772949}, {"id": "https://openalex.org/C205649164", "wikidata": "https://www.wikidata.org/wiki/Q1071", "display_name": "Geography", "level": 0, "score": 0.08632615208625793}, {"id": "https://openalex.org/C127313418", "wikidata": "https://www.wikidata.org/wiki/Q1069", "display_name": "Geology", "level": 0, "score": 0.06977018713951111}, {"id": "https://openalex.org/C166957645", "wikidata": "https://www.wikidata.org/wiki/Q23498", "display_name": "Archaeology", "level": 1, "score": 0.0}, {"id": "https://openalex.org/C172707124", "wikidata": "https://www.wikidata.org/wiki/Q423488", "display_name": "Actuator", "level": 2, "score": 0.0}], "mesh": [], "locations_count": 1, "locations": [{"id": "doi:10.3390/electronics13244912", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/electronics13244912", "pdf_url": "https://www.mdpi.com/2079-9292/13/24/4912/pdf?version=1734017112", "source": {"id": "https://openalex.org/S4210202905", "display_name": "Electronics", "issn_l": "2079-9292", "issn": ["2079-9292"], "is_oa": true, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Electronics", "raw_type": "journal-article"}], "best_oa_location": {"id": "doi:10.3390/electronics13244912", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/electronics13244912", "pdf_url": "https://www.mdpi.com/2079-9292/13/24/4912/pdf?version=1734017112", "source": {"id": "https://openalex.org/S4210202905", "display_name": "Electronics", "issn_l": "2079-9292", "issn": ["2079-9292"], "is_oa": true, "is_in_doaj": false, "is_core": true, "host_organization": "https://openalex.org/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Electronics", "raw_type": "journal-article"}, "sustainable_development_goals": [{"id": "https://metadata.un.org/sdg/9", "score": 0.6200000047683716, "display_name": "Industry, innovation and infrastructure"}], "awards": [], "funders": [], "has_content": {"pdf": true, "grobid_xml": false}, "content_urls": {"pdf": "https://content.openalex.org/works/W4405317693.pdf"}, "referenced_works_count": 87, "referenced_works": ["https://openalex.org/W2913535047", "https://openalex.org/W2941816588", "https://openalex.org/W2975708346", "https://openalex.org/W2991356814", "https://openalex.org/W2997966103", "https://openalex.org/W2998429771", "https://openalex.org/W3021827168", "https://openalex.org/W3084233697", "https://openalex.org/W3114979514", "https://openalex.org/W3131148586", "https://openalex.org/W3133683044", "https://openalex.org/W4200193265", "https://openalex.org/W4205425750", "https://openalex.org/W4205571244", "https://openalex.org/W4210842962", "https://openalex.org/W4212772567", "https://openalex.org/W4213187680", "https://openalex.org/W4225016330", "https://openalex.org/W4225625011", "https://openalex.org/W4281734162", "https://openalex.org/W4282842523", "https://openalex.org/W4283717141", "https://openalex.org/W4284978071", "https://openalex.org/W4285163894", "https://openalex.org/W4287877256", "https://openalex.org/W4293526664", "https://openalex.org/W4303684738", "https://openalex.org/W4309342732", "https://openalex.org/W4312174355", "https://openalex.org/W4312458439", "https://openalex.org/W4313132153", "https://openalex.org/W4313459979", "https://openalex.org/W4313530733", "https://openalex.org/W4317496136", "https://openalex.org/W4319777522", "https://openalex.org/W4319988655", "https://openalex.org/W4327591066", "https://openalex.org/W4328025809", "https://openalex.org/W4328125633", "https://openalex.org/W4362733539", "https://openalex.org/W4363649231", "https://openalex.org/W4367055496", "https://openalex.org/W4376457039", "https://openalex.org/W4378529085", "https://openalex.org/W4378675169", "https://openalex.org/W4379517526", "https://openalex.org/W4380478870", "https://openalex.org/W4380987486", "https://openalex.org/W4383503366", "https://openalex.org/W4384518590", "https://openalex.org/W4384916375", "https://openalex.org/W4384916680", "https://openalex.org/W4385444630", "https://openalex.org/W4385451016", "https://openalex.org/W4385596254", "https://openalex.org/W4386161583", "https://openalex.org/W4386553343", "https://openalex.org/W4386806910", "https://openalex.org/W4387457671", "https://openalex.org/W4387546417", "https://openalex.org/W4387587725", "https://openalex.org/W4387809804", "https://openalex.org/W4388145526", "https://openalex.org/W4388280378", "https://openalex.org/W4388933003", "https://openalex.org/W4388933793", "https://openalex.org/W4389041363", "https://openalex.org/W4389544211", "https://openalex.org/W4389605472", "https://openalex.org/W4389818669", "https://openalex.org/W4390187514", "https://openalex.org/W4390332999", "https://openalex.org/W4392353733", "https://openalex.org/W4392607872", "https://openalex.org/W4393141293", "https://openalex.org/W4393864720", "https://openalex.org/W4399939183", "https://openalex.org/W4400910775", "https://openalex.org/W4401110473", "https://openalex.org/W4402670135", "https://openalex.org/W4403172155", "https://openalex.org/W4403918782", "https://openalex.org/W6850465072", "https://openalex.org/W6851264084", "https://openalex.org/W6857028517", "https://openalex.org/W6859052326", "https://openalex.org/W6859914368"], "related_works": ["https://openalex.org/W86946229", "https://openalex.org/W3009843762", "https://openalex.org/W2054360660", "https://openalex.org/W1998491546", "https://openalex.org/W2913439950", "https://openalex.org/W3097589262", "https://openalex.org/W2127402788", "https://openalex.org/W4376453582", "https://openalex.org/W3147033875", "https://openalex.org/W2078455782"], "abstract_inverted_index": {"In": [0, 75], "this": [1], "paper,": [2], "a": [3, 78, 141, 146], "novel": [4], "multimodal": [5], "large": [6, 56, 93], "language": [7, 57, 94], "model-based": [8], "fault": [9, 20, 49, 68, 101, 121, 135, 150, 179], "detection": [10, 21, 69, 102, 122, 151, 180], "and": [11, 22, 41, 47, 63, 70, 84, 99, 123, 126, 133, 152, 155, 168, 181], "diagnosis": [12, 23, 71, 124, 136, 153, 182], "framework": [13, 29], "that": [14, 81], "addresses": [15], "the": [16, 31, 60, 65, 76, 128, 172], "limitations": [17], "of": [18, 67, 72, 149], "traditional": [19, 120], "approaches": [24], "is": [25, 112], "proposed.": [26], "The": [27], "proposed": [28], "leverages": [30], "Generative": [32], "Pre-trained": [33], "Transformer-4-Preview": [34], "model": [35, 169], "to": [36, 104, 118], "improve": [37], "its": [38], "scalability,": [39], "generalizability,": [40], "efficiency": [42], "in": [43, 177], "handling": [44], "complex": [45], "systems": [46, 183], "various": [48, 159], "scenarios.": [50, 74], "Moreover,": [51], "synthetic": [52], "datasets": [53], "generated": [54], "via": [55], "models": [58, 95], "augment": [59], "knowledge": [61], "base": [62], "enhance": [64], "accuracy": [66], "imbalanced": [73], "framework,": [77], "hybrid": [79], "architecture": [80], "integrates": [82], "online": [83], "offline": [85], "processing,": [86], "combining": [87], "real-time": [88], "data": [89], "streams": [90], "with": [91], "fine-tuned": [92], "for": [96, 174], "dynamic,": [97], "accurate,": [98], "context-aware": [100], "suited": [103], "industrial": [105, 160, 178], "settings,": [106], "particularly": [107], "focusing": [108], "on": [109], "security": [110], "concerns,": [111], "introduced.": [113], "This": [114, 138, 162], "comprehensive": [115], "approach": [116], "aims": [117], "address": [119], "challenges": [125], "advance": [127], "field": [129], "toward": [130], "more": [131], "adaptive": [132], "efficient": [134], "systems.": [137], "paper": [139], "presents": [140], "detailed": [142, 147], "literature": [143], "review,": [144], "including": [145], "taxonomy": [148], "methods": [154], "their": [156], "applications": [157], "across": [158], "domains.": [161], "study": [163, 166], "discusses": [164], "case": [165], "results": [167], "comparisons,": [170], "exploring": [171], "implications": [173], "future": [175], "developments": [176], "within": [184], "Industry": [185], "4.0": [186], "technologies.": [187]}, "counts_by_year": [{"year": 2026, "cited_by_count": 21}, {"year": 2025, "cited_by_count": 26}], "updated_date": "2026-05-21T09:19:25.381259", "created_date": "2025-10-10T00:00:00"}], "group_by": []}