{"id":"https://openalex.org/W4415540666","doi":"https://doi.org/10.1145/3746027.3754716","title":"Enhancing Multi-task Learning Capability of Medical Generalist Foundation Model via Image-centric Multi-annotation Data","display_name":"Enhancing Multi-task Learning Capability of Medical Generalist Foundation Model via Image-centric Multi-annotation Data","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540666","doi":"https://doi.org/10.1145/3746027.3754716"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754716","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754716","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035238722","display_name":"Xun Zhu","orcid":"https://orcid.org/0000-0001-8598-8748"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Zhu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8598-8748","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111183124","display_name":"Fanbin Mo","orcid":"https://orcid.org/0009-0004-0682-9095"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanbin Mo","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0682-9095","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0001-8899-2360"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8899-2360","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075569577","display_name":"J. Wang","orcid":"https://orcid.org/0009-0004-2902-4812"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2902-4812","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036620476","display_name":"Yiming Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Shi","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5335-2803","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077902436","display_name":"Ming Wu","orcid":"https://orcid.org/0000-0001-8390-5398"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Wu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Post and Telecommunication, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8390-5398","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015730388","display_name":"Chuang Zhang","orcid":"https://orcid.org/0000-0002-1115-5580"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China and Beijing Wuzi University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1115-5580","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China and Beijing Wuzi University, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115604944","display_name":"Miao Li","orcid":"https://orcid.org/0009-0009-5672-7448"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5672-7448","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014958566","display_name":"Ji Wu","orcid":"https://orcid.org/0000-0001-6170-726X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China and College of AI, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6170-726X","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China and College of AI, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"2693","last_page":"2702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9955999851226807,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9829000234603882,"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/representation","display_name":"Representation (politics)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.36059999465942383},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35910001397132874},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.35760000348091125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3440000116825104},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3215000033378601},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.3147999942302704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6359000205993652},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217999815940857},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754716","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754716","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2959466714","https://openalex.org/W2964155733","https://openalex.org/W3083720136","https://openalex.org/W4386076522","https://openalex.org/W4389267014","https://openalex.org/W4397005432","https://openalex.org/W4400362569","https://openalex.org/W4401362547","https://openalex.org/W4404356490","https://openalex.org/W4408190450"],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,95,124,147,216,231],"medical":[3,25,96,133,186],"generalist":[4],"foundation":[5],"models":[6,100],"has":[7],"revolutionized":[8],"conventional":[9],"task-specific":[10],"model":[11],"development":[12],"paradigms,":[13],"aiming":[14],"to":[15,40,55,61,89,130,161,180,227],"better":[16],"handle":[17],"multiple":[18],"tasks":[19,149],"through":[20],"joint":[21],"training":[22,152,200,225],"on":[23],"large-scale":[24],"datasets.":[26],"However,":[27],"recent":[28],"advances":[29],"prioritize":[30],"simple":[31],"data":[32,52,104,119,218,235],"scaling":[33],"or":[34,66],"architectural":[35],"component":[36],"enhancement,":[37],"while":[38],"neglecting":[39],"re-examine":[41],"multi-task":[42,92,155,173,209],"learning":[43,93],"from":[44,102,113,178],"a":[45],"data-centric":[46],"perspective.":[47],"Critically,":[48],"simply":[49],"aggregating":[50],"existing":[51],"resources":[53,240],"leads":[54],"decentralized":[56,164],"image-task":[57],"alignment,":[58],"which":[59],"fails":[60],"cultivate":[62],"comprehensive":[63,122],"image":[64,73,141],"understanding":[65],"align":[67],"with":[68,144],"clinical":[69],"needs":[70],"for":[71],"multi-dimensional":[72],"interpretation.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,189,220],"introduce":[79],"the":[80,86,91,103,114,162,213,229],"image-centric":[81],"multi-annotation":[82,165],"X-ray":[83,140,166],"dataset":[84,167],"(IMAX),":[85],"first":[87],"attempt":[88],"enhance":[90],"capabilities":[94],"multi-modal":[97],"large":[98],"language":[99],"(MLLMs)":[101],"construction":[105],"level.":[106],"To":[107],"be":[108],"specific,":[109],"IMAX":[110,169,197,217,234],"is":[111,142],"featured":[112],"following":[115],"attributes:":[116],"1)":[117],"High-quality":[118],"curation.":[120],"A":[121],"collection":[123],"more":[125],"than":[126],"354K":[127],"entries":[128],"applicable":[129],"seven":[131,183],"different":[132],"tasks.":[134],"2)":[135],"Image-centric":[136],"dense":[137],"annotation.":[138],"Each":[139],"associated":[143],"an":[145,222],"average":[146,174],"4.10":[148],"and":[150,198,208],"7.46":[151],"entries,":[153],"ensuring":[154],"representation":[156],"richness":[157],"per":[158],"image.":[159],"Compared":[160],"general":[163],"(DMAX),":[168],"consistently":[170],"demonstrates":[171],"significant":[172],"performance":[175],"gains":[176],"ranging":[177],"3.20%":[179],"21.05%":[181],"across":[182],"open-source":[184],"state-of-the-art":[185],"MLLMs.":[187],"Moreover,":[188],"investigate":[190],"differences":[191],"in":[192,236],"statistical":[193],"patterns":[194],"exhibited":[195],"by":[196],"DMAX":[199],"processes,":[201],"exploring":[202],"potential":[203],"correlations":[204],"between":[205],"optimization":[206],"dynamics":[207],"performance.":[210],"Finally,":[211],"leveraging":[212],"core":[214],"concept":[215],"construction,":[219],"propose":[221],"optimized":[223],"DMAX-based":[224],"strategy":[226],"alleviate":[228],"dilemma":[230],"obtaining":[232],"high-quality":[233],"practical":[237],"scenarios.":[238],"Related":[239],"are":[241],"available":[242],"at":[243],"https://github.com/MSIIP/IMAX.":[244]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}