{"id":"https://openalex.org/W4401109855","doi":"https://doi.org/10.1109/tpami.2024.3435790","title":"MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation","display_name":"MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation","publication_year":2024,"publication_date":"2024-07-30","ids":{"openalex":"https://openalex.org/W4401109855","doi":"https://doi.org/10.1109/tpami.2024.3435790","pmid":"https://pubmed.ncbi.nlm.nih.gov/39078756"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3435790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3435790","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":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0001-5334-1843","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-5110-4526","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029317372","display_name":"Minglang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglang Huang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052555143","display_name":"Tianhe Ren","orcid":"https://orcid.org/0000-0003-3121-4020"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhe Ren","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9734,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73929624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"47","issue":"7","first_page":"5192","last_page":"5204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9851999878883362,"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":0.9851999878883362,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6449458599090576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6132256984710693},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6125262975692749},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6063229441642761},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46289247274398804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3230525851249695},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22138488292694092},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.1501816213130951},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12691783905029297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449458599090576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6132256984710693},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6125262975692749},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6063229441642761},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46289247274398804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3230525851249695},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22138488292694092},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.1501816213130951},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12691783905029297},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3435790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3435790","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:39078756","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39078756","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2989602205","display_name":null,"funder_award_id":"623B200373","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G602081181","display_name":null,"funder_award_id":"2022ZD0118201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2560730294","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2963912046","https://openalex.org/W2970231061","https://openalex.org/W2989743967","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3153675281","https://openalex.org/W3173220247","https://openalex.org/W3174702398","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W3177323791","https://openalex.org/W3198377975","https://openalex.org/W3201174429","https://openalex.org/W3208314443","https://openalex.org/W3213454282","https://openalex.org/W4205991051","https://openalex.org/W4221145545","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312884055","https://openalex.org/W4312933868","https://openalex.org/W4321276845","https://openalex.org/W4378510493","https://openalex.org/W4385245566","https://openalex.org/W4386071687","https://openalex.org/W4386187806","https://openalex.org/W6620707391","https://openalex.org/W6743367031","https://openalex.org/W6759579507","https://openalex.org/W6766904570","https://openalex.org/W6775188310","https://openalex.org/W6784333009","https://openalex.org/W6789505266","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6798805250","https://openalex.org/W6802744804","https://openalex.org/W6803476161","https://openalex.org/W6810447287","https://openalex.org/W6839091850","https://openalex.org/W6839562487","https://openalex.org/W6843405348","https://openalex.org/W6850625674","https://openalex.org/W6851629679","https://openalex.org/W6851948999","https://openalex.org/W6854347851","https://openalex.org/W6858704499"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2058170566","https://openalex.org/W4306674287","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Pre-training":[0],"and":[1,43,78,118,148,213,226,258,270],"fine-tuning":[2,20,54],"have":[3],"been":[4],"the":[5,13,53,98,113,151,156,174,189,193],"de-facto":[6],"paradigm":[7],"in":[8,38],"vision-language":[9,23],"domains.":[10],"Along":[11],"with":[12],"rapid":[14],"growth":[15],"of":[16,55,101,155,177,192,229],"model":[17,58],"sizes,":[18],"fully":[19],"these":[21,181],"large-scale":[22],"pre-training":[24],"(VLP)":[25],"models":[26,77,205],"requires":[27],"prohibitively":[28],"expensive":[29],"storage":[30],"costs.":[31],"To":[32],"address":[33],"this":[34,92,122,161],"issue,":[35],"recent":[36],"advances":[37],"NLP":[39],"offer":[40],"a":[41,71,108,126,143,167],"promising":[42],"efficient":[44],"adaptation":[45,103],"approach":[46],"called":[47],"LoRA,":[48],"which":[49,84],"aims":[50],"to":[51,172,210],"approximate":[52],"large":[56,72],"pre-trained":[57],"by":[59,107,237,248,264],"updating":[60,238],"low-rank":[61,102,157,178,194],"parameters.":[62],"Despite":[63],"its":[64,79,87,255],"effectiveness,":[65],"we":[66,94,124,164],"identify":[67],"that":[68,97],"LoRA":[69,117],"suffers":[70],"approximation":[73,99,152,170],"error":[74,100,153],"on":[75,121,160,196,202,217,250],"VLP":[76,131,197,204,266],"optimization":[80,110,190,227],"is":[81,261],"also":[82,165,262],"inefficient,":[83],"greatly":[85,187],"limits":[86],"performance":[88,225],"upper":[89],"bound.":[90],"In":[91],"paper,":[93],"mathematically":[95],"prove":[96],"can":[104,186,243],"be":[105],"optimized":[106],"new":[109,168],"objective,":[111],"i.e.,":[112],"weight":[114,144],"distance":[115],"between":[116],"fine-tuning.":[119],"Based":[120,159],"finding,":[123],"propose":[125],"novel":[127,183],"PETL":[128,141,233],"method":[129],"for":[130],"models,":[132,267],"namely":[133],"momentum":[134],"imitation":[135,145],"learning":[136,146,175],"(MoIL).":[137],"Specifically,":[138],"MoIL":[139,185,201,230,242],"formulates":[140],"as":[142],"process":[147],"directly":[149],"optimize":[150],"bound":[154],"adaptation.":[158],"training":[162],"scheme,":[163],"explore":[166],"hybrid":[169],"function":[171],"reduce":[173],"difficulty":[176],"adaptations.":[179],"With":[180],"two":[182],"designs,":[184],"improve":[188],"efficiency":[191,228,257],"parameters":[195],"models.":[198],"We":[199],"validate":[200],"three":[203],"ranging":[206],"from":[207],"end-to-end":[208],"network":[209],"two-stage":[211],"network,":[212],"conduct":[214],"extensive":[215],"experiments":[216],"four":[218],"VL":[219],"tasks.":[220],"Experimental":[221],"results":[222],"demonstrate":[223],"superior":[224],"than":[231],"existing":[232],"methods.":[234],"For":[235],"instance,":[236],"only":[239],"6.23%":[240],"parameters,":[241],"even":[244],"outperform":[245],"full":[246],"tuning":[247],"+2.3%":[249],"image-text":[251],"matching":[252],"task.":[253],"Meanwhile,":[254],"inference":[256],"generalization":[259],"ability":[260],"validated":[263],"multiple":[265],"e.g.,":[268],"VLMO":[269],"VinVL.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}