{"id":"https://openalex.org/W4406231658","doi":"https://doi.org/10.1109/iccv51701.2025.01641","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","display_name":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406231658","doi":"https://doi.org/10.1109/iccv51701.2025.01641"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.04670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104162474","display_name":"Yikang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yikang Zhou","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375748","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-9470-7215"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068311346","display_name":"Shilin Xu","orcid":"https://orcid.org/0009-0009-1198-3739"},"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":"Shilin Xu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055000437","display_name":"Shihao Chen","orcid":"https://orcid.org/0000-0001-7646-8003"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Chen","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111039855","display_name":"Qianyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianyu Zhou","raw_affiliation_strings":["SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SJTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097240","display_name":"Yunhai Tong","orcid":"https://orcid.org/0000-0001-8735-2516"},"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":"Yunhai Tong","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031588692","display_name":"Shunping Ji","orcid":"https://orcid.org/0000-0002-3088-1481"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunping Ji","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033141976","display_name":"Jiansheng Zhang","orcid":"https://orcid.org/0009-0009-2693-0883"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665478","display_name":"Qi Lu","orcid":"https://orcid.org/0000-0002-3596-2774"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Qi","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17663","last_page":"17674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.986299991607666,"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"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.986299991607666,"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"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.9846000075340271,"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"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.9811999797821045,"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/psychology","display_name":"Psychology","score":0.35192638635635376}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35192638635635376}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.04670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04670","pdf_url":"https://arxiv.org/pdf/2501.04670","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.04670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.04670","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.04670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04670","pdf_url":"https://arxiv.org/pdf/2501.04670","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W3006817050","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W2067108088"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,13,40,50],"multimodal":[3],"large":[4],"language":[5],"models":[6,244],"(MLLM)":[7],"have":[8,125],"shown":[9],"a":[10,68,165],"strong":[11,60],"ability":[12,25],"visual":[14,23,34,139,152],"perception,":[15],"reasoning":[16,143],"abilities,":[17],"and":[18,90,112,118,155,181,213,221,235,243],"vision-language":[19],"understanding.":[20],"However,":[21],"the":[22,33,47,98,109,133,150,158,192,208,214,228],"matching":[24,48,140],"of":[26,36,101,205,230],"MLLMs":[27,52,61],"is":[28,38,84,149],"rarely":[29],"studied,":[30],"despite":[31],"finding":[32],"correspondence":[35],"objects":[37],"essential":[39],"computer":[41],"vision.":[42],"Our":[43],"research":[44],"reveals":[45],"that":[46],"capabilities":[49,113],"recent":[51],"still":[53],"exhibit":[54],"systematic":[55],"shortcomings,":[56],"even":[57],"with":[58,93,142,169,177],"current":[59,120],"models,":[62],"GPT-4o.":[63],"In":[64,122],"particular,":[65],"we":[66,124,162],"construct":[67],"Multimodal":[69],"Visual":[70],"Matching":[71],"(MMVM)":[72],"benchmark":[73,76,83,103,156],"to":[74,114,131],"fairly":[75],"over":[77],"30":[78],"different":[79],"MLLMs.":[80,121],"The":[81,185],"MMVM":[82,102,134,209,232],"built":[85],"from":[86],"15":[87],"open-source":[88,216],"datasets":[89],"Internet":[91],"videos":[92],"manual":[94],"annotation.":[95,144],"We":[96],"categorize":[97],"data":[99,141],"samples":[100],"into":[104],"eight":[105],"aspects":[106],"based":[107],"on":[108,207],"required":[110],"cues":[111],"more":[115],"comprehensively":[116],"evaluate":[117],"analyze":[119],"addition,":[123],"designed":[126],"an":[127,201],"automatic":[128],"annotation":[129],"pipeline":[130],"generate":[132],"SFT":[135,233],"dataset,":[136,242],"including":[137],"220K":[138],"To":[145],"our":[146,231,236],"knowledge,":[147],"this":[148],"first":[151],"corresponding":[153],"dataset":[154,234],"for":[157],"MLLM":[159,168],"community.":[160],"Finally,":[161],"present":[163],"CoLVA,":[164],"novel":[166,171,237],"contrastive":[167,179],"two":[170],"technical":[172,238],"designs:":[173],"fine-grained":[174],"vision":[175],"expert":[176],"object-level":[178],"learning":[180],"instruction":[182,196],"augmentation":[183],"strategy.":[184],"former":[186],"learns":[187],"instance":[188],"discriminative":[189],"tokens,":[190],"while":[191],"latter":[193],"further":[194],"improves":[195],"following":[197],"ability.":[198],"CoLVA-InternVL2-4B":[199],"achieves":[200],"overall":[202],"accuracy":[203],"(OA)":[204],"49.80\\%":[206],"benchmark,":[210,241],"surpassing":[211],"GPT-4o":[212],"best":[215],"MLLM,":[217],"Qwen2VL-72B,":[218],"by":[219],"7.15\\%":[220],"11.72\\%":[222],"OA,":[223],"respectively.":[224],"These":[225],"results":[226],"demonstrate":[227],"effectiveness":[229],"designs.":[239],"Code,":[240],"will":[245],"be":[246],"released.":[247]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}