{"id":"https://openalex.org/W4413849607","doi":"https://doi.org/10.1007/s11263-025-02572-7","title":"Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A Survey","display_name":"Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A Survey","publication_year":2025,"publication_date":"2025-08-30","ids":{"openalex":"https://openalex.org/W4413849607","doi":"https://doi.org/10.1007/s11263-025-02572-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02572-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02572-7","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/A5074027508","display_name":"Jiaxing Huang","orcid":"https://orcid.org/0000-0001-9176-8901"},"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":"Jiaxing Huang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458616","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0002-0931-1302"},"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":"Jingyi Zhang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010999540","display_name":"Kai Jiang","orcid":"https://orcid.org/0000-0002-5706-7834"},"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":"Kai Jiang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019692903","display_name":"Han Qiu","orcid":"https://orcid.org/0000-0003-2678-8070"},"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":"Han Qiu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699785","display_name":"Xiaoqin Zhang","orcid":"https://orcid.org/0000-0003-0958-7285"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082634513","display_name":"Ling Shao","orcid":"https://orcid.org/0000-0002-8264-6117"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Shao","raw_affiliation_strings":["UCAS-Terminus AI Lab, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCAS-Terminus AI Lab, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"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":"Shijian Lu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6766-2506","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"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":"Dacheng Tao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023507910"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":3.8276,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.94123856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"133","issue":"11","first_page":"8151","last_page":"8189"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926000237464905,"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":0.9912999868392944,"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":0.6930146217346191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5593410730361938},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4598774015903473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40678006410598755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36735671758651733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930146217346191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5593410730361938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4598774015903473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40678006410598755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36735671758651733}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-025-02572-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02572-7","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:10356/204631","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/204631","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1977295328","https://openalex.org/W2031489346","https://openalex.org/W2052533453","https://openalex.org/W2108598243","https://openalex.org/W2155904486","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2470139095","https://openalex.org/W2533598788","https://openalex.org/W2560730294","https://openalex.org/W2594519801","https://openalex.org/W2606982687","https://openalex.org/W2612690371","https://openalex.org/W2618530766","https://openalex.org/W2765716052","https://openalex.org/W2794284562","https://openalex.org/W2901466771","https://openalex.org/W2904565150","https://openalex.org/W2947312908","https://openalex.org/W2948672349","https://openalex.org/W2948685905","https://openalex.org/W2963037989","https://openalex.org/W2963109634","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2964220823","https://openalex.org/W2979382951","https://openalex.org/W2989322838","https://openalex.org/W2990138404","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3104279398","https://openalex.org/W3109340983","https://openalex.org/W3120043490","https://openalex.org/W3165058054","https://openalex.org/W3173585224","https://openalex.org/W3198377975","https://openalex.org/W4221138790","https://openalex.org/W4226376247","https://openalex.org/W4285255856","https://openalex.org/W4285618474","https://openalex.org/W4312270234","https://openalex.org/W4312563428","https://openalex.org/W4312651322","https://openalex.org/W4385570412","https://openalex.org/W4386065884","https://openalex.org/W4386075660","https://openalex.org/W4389519587","https://openalex.org/W4389519620","https://openalex.org/W4389523832","https://openalex.org/W4389903841","https://openalex.org/W4390874575","https://openalex.org/W4391094120","https://openalex.org/W4392172801","https://openalex.org/W4393149524","https://openalex.org/W4393159297","https://openalex.org/W4400362569","https://openalex.org/W4400647053","https://openalex.org/W4401024018","https://openalex.org/W4401386967","https://openalex.org/W4402669775","https://openalex.org/W4402670135","https://openalex.org/W4402670537","https://openalex.org/W4402670747","https://openalex.org/W4402670813","https://openalex.org/W4402671548","https://openalex.org/W4402713111","https://openalex.org/W4402716166","https://openalex.org/W4402716381","https://openalex.org/W4402716423","https://openalex.org/W4402727018","https://openalex.org/W4402727272","https://openalex.org/W4402727558","https://openalex.org/W4402727669","https://openalex.org/W4402727755","https://openalex.org/W4402727764","https://openalex.org/W4402727789","https://openalex.org/W4402727922","https://openalex.org/W4402753874","https://openalex.org/W4402753980","https://openalex.org/W4402754134","https://openalex.org/W4402754238","https://openalex.org/W4403081466","https://openalex.org/W4403476856","https://openalex.org/W4403587166","https://openalex.org/W4403625924","https://openalex.org/W4403705976","https://openalex.org/W4403778769","https://openalex.org/W4403792205","https://openalex.org/W4403938642","https://openalex.org/W4404356490","https://openalex.org/W4404544903","https://openalex.org/W4404563230","https://openalex.org/W4404582572","https://openalex.org/W4404582879","https://openalex.org/W4404654668","https://openalex.org/W4404654684","https://openalex.org/W4404780528","https://openalex.org/W4404782218","https://openalex.org/W4404782797","https://openalex.org/W4404783556","https://openalex.org/W4405102058","https://openalex.org/W4408615011","https://openalex.org/W4413147327"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}