{"id":"https://openalex.org/W4410536678","doi":"https://doi.org/10.1109/tpami.2025.3571946","title":"Otter: A Multi-Modal Model With In-Context Instruction Tuning","display_name":"Otter: A Multi-Modal Model With In-Context Instruction Tuning","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410536678","doi":"https://doi.org/10.1109/tpami.2025.3571946","pmid":"https://pubmed.ncbi.nlm.nih.gov/40392642"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3571946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3571946","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-8447-0928"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-8447-0928","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677327","display_name":"Yuanhan Zhang","orcid":"https://orcid.org/0000-0002-9063-7886"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yuanhan Zhang","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-9063-7886","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liangyu Chen","orcid":"https://orcid.org/0000-0002-5181-8457"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Liangyu Chen","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-5181-8457","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinghao Wang","orcid":"https://orcid.org/0009-0009-5919-5328"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Jinghao Wang","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0009-0009-5919-5328","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109714657","display_name":"Fanyi Pu","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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Fanyi Pu","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100029751","display_name":"Joshua Adrian Cahyono","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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Joshua Adrian Cahyono","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingkang Yang","orcid":"https://orcid.org/0000-0002-2923-3137"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Jingkang Yang","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-2923-3137","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107893340","display_name":"Chunyuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyuan Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, Redmond, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"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"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-4220-5958","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":57.5342,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.99959631,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"47","issue":"9","first_page":"7543","last_page":"7557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9718999862670898,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9718999862670898,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9553999900817871,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9456999897956848,"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/context","display_name":"Context (archaeology)","score":0.6624470353126526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6488584280014038},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6027466058731079},{"id":"https://openalex.org/keywords/otter","display_name":"Otter","score":0.513295590877533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5057523250579834},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4607715308666229},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13453713059425354},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11999925971031189},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.08782878518104553}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6624470353126526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6488584280014038},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6027466058731079},{"id":"https://openalex.org/C2776931103","wikidata":"https://www.wikidata.org/wiki/Q200184","display_name":"Otter","level":2,"score":0.513295590877533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5057523250579834},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4607715308666229},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13453713059425354},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11999925971031189},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.08782878518104553},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3571946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3571946","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40392642","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40392642","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218198","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218198","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":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1927052826","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2549599535","https://openalex.org/W2560730294","https://openalex.org/W2594519801","https://openalex.org/W2765716052","https://openalex.org/W2886641317","https://openalex.org/W2947312908","https://openalex.org/W2962749469","https://openalex.org/W2963518342","https://openalex.org/W2963916161","https://openalex.org/W2964220823","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3104862079","https://openalex.org/W3107521863","https://openalex.org/W3176641147","https://openalex.org/W3198377975","https://openalex.org/W4307079201","https://openalex.org/W4310509152","https://openalex.org/W4311726128","https://openalex.org/W4312310776","https://openalex.org/W4312846625","https://openalex.org/W4380137126","https://openalex.org/W4382763281","https://openalex.org/W4385567149","https://openalex.org/W4385570412","https://openalex.org/W4385570745","https://openalex.org/W4385570984","https://openalex.org/W4385571886","https://openalex.org/W4385572634","https://openalex.org/W4385572845","https://openalex.org/W4389523832","https://openalex.org/W4402727516","https://openalex.org/W4402727764","https://openalex.org/W4402951693","https://openalex.org/W4403081466","https://openalex.org/W4404575065","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6800875267","https://openalex.org/W6802669662","https://openalex.org/W6802987763","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6845868278","https://openalex.org/W6846007759","https://openalex.org/W6849177959","https://openalex.org/W6849923734","https://openalex.org/W6850625674","https://openalex.org/W6850822301","https://openalex.org/W6851592950","https://openalex.org/W6851938174","https://openalex.org/W6851948999","https://openalex.org/W6851950068","https://openalex.org/W6851960618","https://openalex.org/W6852060543","https://openalex.org/W6852489829","https://openalex.org/W6852776751","https://openalex.org/W6853116092","https://openalex.org/W6853299509","https://openalex.org/W6854093740","https://openalex.org/W6854262950","https://openalex.org/W6854263694","https://openalex.org/W6855297460","https://openalex.org/W6855350031","https://openalex.org/W6855815363","https://openalex.org/W6856032414","https://openalex.org/W6858147810"],"related_works":["https://openalex.org/W2349222429","https://openalex.org/W2116230991","https://openalex.org/W3117430770","https://openalex.org/W2046058552","https://openalex.org/W2590751808","https://openalex.org/W1972377868","https://openalex.org/W2132709506","https://openalex.org/W2098730537","https://openalex.org/W2186895195","https://openalex.org/W2748557612"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,189],"Large":[3],"Multimodal":[4],"Models":[5],"(LMMs)":[6],"have":[7],"unveiled":[8],"great":[9],"potential":[10],"as":[11,41],"visual":[12,64],"assistants.":[13],"However,":[14],"most":[15],"existing":[16],"works":[17],"focus":[18],"on":[19,35],"responding":[20],"to":[21,44,59,145,187],"individual":[22],"instructions":[23,131],"or":[24],"using":[25],"previous":[26],"dialogues":[27],"for":[28,67,83,153],"contextual":[29],"understanding.":[30,196],"There":[31],"is":[32],"little":[33],"discussion":[34],"employing":[36],"both":[37,61],"images":[38,137],"and":[39,63,78,99,138,170,194],"text":[40],"in-context":[42,65,151,164],"examples":[43,66,152,165],"enhance":[45],"the":[46,56,105,111,174,180,184],"instruction":[47,68,81,160],"following":[48],"capability.":[49],"To":[50,103],"bridge":[51],"this":[52],"gap,":[53],"we":[54,109],"introduce":[55],"Otter":[57,71,88,185],"model":[58,168,186],"leverage":[60],"textual":[62],"tuning.":[69],"Specifically,":[70],"builds":[72],"upon":[73],"Flamingo":[74],"with":[75,162],"Perceiver":[76],"architecture,":[77],"has":[79,141],"been":[80,142],"tuned":[82],"general":[84],"purpose":[85],"multi-modal":[86,91,123],"assistant.":[87],"seamlessly":[89],"processes":[90],"inputs,":[92],"supporting":[93],"modalities":[94],"including":[95,126],"text,":[96],"multiple":[97],"images,":[98],"dynamic":[100],"video":[101,193],"content.":[102],"support":[104],"training":[106],"of":[107,136,150],"Otter,":[108],"present":[110],"MIMIC-IT":[112,140,181],"(MultI-Modal":[113],"In-Context":[114],"Instruction":[115],"Tuning)":[116],"dataset,":[117],"which":[118],"encompasses":[119],"over":[120],"3":[121],"million":[122,129],"instruction-response":[124],"pairs,":[125],"approximately":[127],"2.2":[128],"unique":[130],"across":[132],"a":[133,147],"broad":[134],"spectrum":[135],"videos.":[139],"carefully":[143],"curated":[144],"feature":[146],"diverse":[148],"array":[149],"each":[154],"entry.":[155],"Comprehensive":[156],"evaluations":[157],"suggest":[158],"that":[159],"tuning":[161],"these":[163],"substantially":[166],"enhances":[167],"convergence":[169],"generalization":[171],"capabilities.":[172],"Notably,":[173],"extensive":[175],"scenario":[176],"coverage":[177],"provided":[178],"by":[179],"dataset":[182],"empowers":[183],"excel":[188],"tasks":[190],"involving":[191],"complex":[192],"multi-image":[195]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2025-10-10T00:00:00"}