{"id":"https://openalex.org/W4403906565","doi":"https://doi.org/10.1007/978-3-031-73033-7_3","title":"SPHINX: A Mixer of\u00a0Weights, Visual Embeddings and\u00a0Image Scales for\u00a0Multi-modal Large Language Models","display_name":"SPHINX: A Mixer of\u00a0Weights, Visual Embeddings and\u00a0Image Scales for\u00a0Multi-modal Large Language Models","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403906565","doi":"https://doi.org/10.1007/978-3-031-73033-7_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-73033-7_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73033-7_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5009429165","display_name":"Ziyi Lin","orcid":"https://orcid.org/0009-0002-5336-4193"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ziyi Lin","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761789","display_name":"Dongyang Liu","orcid":"https://orcid.org/0000-0003-3342-8356"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyang Liu","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891082","display_name":"Renrui Zhang","orcid":"https://orcid.org/0000-0003-4503-5277"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renrui Zhang","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596659","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0001-5669-9007"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089497160","display_name":"Longtian Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longtian Qiu","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xiao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101033344","display_name":"Han Qiu","orcid":"https://orcid.org/0009-0005-3691-6226"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Qiu","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827257","display_name":"Wenqi Shao","orcid":"https://orcid.org/0000-0003-3781-4086"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Shao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030987813","display_name":"Keqin Chen","orcid":"https://orcid.org/0000-0002-9091-8258"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqin Chen","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005276003","display_name":"Jiaming Han","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaming Han","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101857439","display_name":"Siyuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Huang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444201","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-3214-1070"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015970030","display_name":"Xuming He","orcid":"https://orcid.org/0000-0003-2150-1237"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming He","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101371688","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0001-8932-7621"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732454","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0003-1040-4108"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence Limited, Hong Kong, China","Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence Limited, Hong Kong, China","institution_ids":[]},{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5009429165"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I4391012619"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":8.0093,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.98481445,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"55"},"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":0.9976000189781189,"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":0.9941999912261963,"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":0.8359427452087402},{"id":"https://openalex.org/keywords/sphinx","display_name":"Sphinx","score":0.705027163028717},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6862567067146301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5266810655593872},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44465872645378113},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41173070669174194},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3989759683609009},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3825921416282654},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.054107606410980225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359427452087402},{"id":"https://openalex.org/C2777299493","wikidata":"https://www.wikidata.org/wiki/Q151480","display_name":"Sphinx","level":2,"score":0.705027163028717},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6862567067146301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266810655593872},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44465872645378113},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41173070669174194},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3989759683609009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825921416282654},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.054107606410980225},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-73033-7_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73033-7_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2560023338","https://openalex.org/W2563399268","https://openalex.org/W2565639579","https://openalex.org/W2568262903","https://openalex.org/W2947312908","https://openalex.org/W2948672349","https://openalex.org/W2963109634","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3106859150","https://openalex.org/W3135367836","https://openalex.org/W3199003182","https://openalex.org/W3212452301","https://openalex.org/W4221155125","https://openalex.org/W4225323055","https://openalex.org/W4226278401","https://openalex.org/W4281633595","https://openalex.org/W4296605665","https://openalex.org/W4312446817","https://openalex.org/W4312605942","https://openalex.org/W4312846625","https://openalex.org/W4312933868","https://openalex.org/W4381802186","https://openalex.org/W4386065815","https://openalex.org/W4386071707","https://openalex.org/W4386075985","https://openalex.org/W4386076493","https://openalex.org/W4389520072","https://openalex.org/W4389523832","https://openalex.org/W4390874324","https://openalex.org/W4402716381","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W4403778769","https://openalex.org/W4404612908","https://openalex.org/W6600008909","https://openalex.org/W6600213211","https://openalex.org/W6600234944","https://openalex.org/W6600574797","https://openalex.org/W6600669965","https://openalex.org/W6600756316","https://openalex.org/W6601076540","https://openalex.org/W6601202783","https://openalex.org/W6601804787","https://openalex.org/W6602254124","https://openalex.org/W6603281439","https://openalex.org/W6607643177","https://openalex.org/W6702248584","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W1982207645","https://openalex.org/W2952747254","https://openalex.org/W2079104883","https://openalex.org/W2078462251","https://openalex.org/W2616994625","https://openalex.org/W2285278858","https://openalex.org/W4251811912","https://openalex.org/W2029530604","https://openalex.org/W2941377492","https://openalex.org/W2178379997"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
