{"id":"https://openalex.org/W4413145922","doi":"https://doi.org/10.1109/cvpr52734.2025.02865","title":"Multi-modal Medical Diagnosis via Large-small Model Collaboration","display_name":"Multi-modal Medical Diagnosis via Large-small Model Collaboration","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145922","doi":"https://doi.org/10.1109/cvpr52734.2025.02865"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041485645","display_name":"Wanyi Chen","orcid":"https://orcid.org/0000-0002-8675-6567"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyi Chen","raw_affiliation_strings":["Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102705176","display_name":"Zihua Zhao","orcid":"https://orcid.org/0000-0001-8611-8656"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihua Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210099312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922412","display_name":"Jiangchao Yao","orcid":"https://orcid.org/0000-0001-6115-5194"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangchao Yao","raw_affiliation_strings":["Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210099312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047118636","display_name":"Haishuai Wang","orcid":"https://orcid.org/0000-0003-1617-0920"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishuai Wang","raw_affiliation_strings":["Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Scence","institution_ids":["https://openalex.org/I4210123185"]}]}],"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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30763","last_page":"30773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5622000098228455,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5622000098228455,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5102999806404114,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6877737641334534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6368612051010132},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1025795042514801}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6877737641334534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6368612051010132},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1025795042514801},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"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/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,13],"medical":[3,21,32,65,88,141,167],"AI":[4],"have":[5],"shown":[6],"a":[7,27,77,94,102,162],"clear":[8],"trend":[9],"towards":[10],"large":[11,17,67,89,123],"models":[12,18,38,68],"healthcare.":[14],"However,":[15],"developing":[16],"for":[19,165],"multi-modal":[20,36,70,103,140],"diagnosis":[22,168],"remains":[23],"challenging":[24],"due":[25],"to":[26,81,99],"lack":[28],"of":[29,131],"sufficient":[30],"modal-complete":[31],"data.":[33],"Most":[34],"existing":[35],"diagnostic":[37,152],"are":[39],"relatively":[40],"small":[41,71,104,133],"and":[42,91,126,144,150],"struggle":[43],"with":[44,69,101],"limited":[45],"feature":[46],"extraction":[47],"capabilities.":[48],"To":[49],"bridge":[50],"this":[51],"gap,":[52],"we":[53],"propose":[54],"AdaCoMed,":[55],"an":[56,111],"adaptive":[57,96,112],"collaborative-learning":[58],"framework":[59,74],"that":[60],"synergistically":[61],"integrates":[62],"the":[63,117,121,127,132],"off-the-shelf":[64],"single-modal":[66,87],"models.":[72],"Our":[73],"first":[75],"employs":[76],"mixture-of-modality-experts":[78],"(MoME)":[79],"architecture":[80],"combine":[82],"features":[83,125],"extracted":[84],"from":[85],"multiple":[86],"models,":[90],"then":[92],"introduces":[93],"novel":[95],"co-learning":[97,107],"mechanism":[98],"collaborate":[100],"model.":[105,134],"This":[106],"mechanism,":[108],"guided":[109],"by":[110],"weighting":[113],"strategy,":[114],"dynamically":[115],"balances":[116],"complementary":[118],"strengths":[119],"between":[120],"MoMEfused":[122],"model":[124],"cross-modal":[128],"reasoning":[129],"capabilities":[130],"Extensive":[135],"experiments":[136],"on":[137],"two":[138],"representative":[139],"datasets":[142],"(MIMICIV-MM":[143],"MMIST":[145],"ccRCC)":[146],"across":[147],"six":[148],"modalities":[149],"four":[151],"tasks":[153],"demonstrate":[154],"consistent":[155],"improvements":[156],"over":[157],"state-of-the-art":[158],"baselines,":[159],"making":[160],"it":[161],"promising":[163],"solution":[164],"real-world":[166],"applications.":[169],"The":[170],"code":[171],"is":[172],"available":[173],"at":[174],"https://github.com/Zoew420/AdaCoMed.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
