{"id":"https://openalex.org/W4413155746","doi":"https://doi.org/10.1109/cvpr52734.2025.02303","title":"MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output","display_name":"MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155746","doi":"https://doi.org/10.1109/cvpr52734.2025.02303"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02303","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":"article","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/A5104230937","display_name":"Yanyuan Chen","orcid":"https://orcid.org/0000-0003-1579-5857"},"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":true,"raw_author_name":"Yanyuan Chen","raw_affiliation_strings":["Peking University,School of Software &amp; Microelectronics"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software &amp; Microelectronics","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025770","display_name":"Dexuan Xu","orcid":null},"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":"Dexuan Xu","raw_affiliation_strings":["Peking University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102204918","display_name":"Yu Huang","orcid":null},"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"]},{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":["Peking University,National Engineering Research Center for Software Engineering"],"affiliations":[{"raw_affiliation_string":"Peking University,National Engineering Research Center for Software Engineering","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070369468","display_name":"Siyan Zhan","orcid":"https://orcid.org/0000-0001-7252-5349"},"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":"Songkun Zhan","raw_affiliation_strings":["Peking University,School of Software &amp; Microelectronics"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software &amp; Microelectronics","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079106687","display_name":"Hanpin Wang","orcid":null},"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":"Hanpin Wang","raw_affiliation_strings":["Peking University,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054837807","display_name":"Dongxue Chen","orcid":"https://orcid.org/0000-0002-7440-4230"},"institutions":[{"id":"https://openalex.org/I4210162420","display_name":"Peking University Sixth Hospital","ror":"https://ror.org/05rzcwg85","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210162420"]},{"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":"Dongxue Chen","raw_affiliation_strings":["Peking University Sixth Hospital"],"affiliations":[{"raw_affiliation_string":"Peking University Sixth Hospital","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210162420"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683372","display_name":"Xueping Wang","orcid":"https://orcid.org/0000-0002-3010-5685"},"institutions":[{"id":"https://openalex.org/I4210162420","display_name":"Peking University Sixth Hospital","ror":"https://ror.org/05rzcwg85","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210162420"]},{"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":"Xueping Wang","raw_affiliation_strings":["Peking University Sixth Hospital"],"affiliations":[{"raw_affiliation_string":"Peking University Sixth Hospital","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210162420"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083330935","display_name":"Meikang Qiu","orcid":"https://orcid.org/0000-0002-1004-0140"},"institutions":[{"id":"https://openalex.org/I4210087454","display_name":"Augusta University Health","ror":"https://ror.org/007rawr89","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meikang Qiu","raw_affiliation_strings":["Augusta University"],"affiliations":[{"raw_affiliation_string":"Augusta University","institution_ids":["https://openalex.org/I4210087454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455142","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-7343-3865"},"institutions":[{"id":"https://openalex.org/I4210130930","display_name":"Peking University First Hospital","ror":"https://ror.org/02z1vqm45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210130930"]},{"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":"Hang Li","raw_affiliation_strings":["Peking University First Hospital"],"affiliations":[{"raw_affiliation_string":"Peking University First Hospital","institution_ids":["https://openalex.org/I4210130930","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5104230937"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":7.0966,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9717762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24732","last_page":"24741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9848999977111816,"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":0.9848999977111816,"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/T12031","display_name":"Speech and dialogue systems","score":0.9150999784469604,"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/computer-science","display_name":"Computer science","score":0.7178891897201538},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6219049096107483},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.565047025680542},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5551191568374634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5268199443817139},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.5254085063934326},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3456626534461975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11691415309906006},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09628605842590332},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08222943544387817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178891897201538},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6219049096107483},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.565047025680542},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5551191568374634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5268199443817139},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.5254085063934326},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3456626534461975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11691415309906006},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09628605842590332},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08222943544387817},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02303","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2895298210","https://openalex.org/W2901466771","https://openalex.org/W2963115613","https://openalex.org/W2968101724","https://openalex.org/W3165058054","https://openalex.org/W4382517509","https://openalex.org/W4386076142","https://openalex.org/W4390874575","https://openalex.org/W4402683905","https://openalex.org/W4402727018","https://openalex.org/W4402753283","https://openalex.org/W4404575065","https://openalex.org/W4404782407"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W1537063595","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W2379604501","https://openalex.org/W2373854414","https://openalex.org/W2574906695","https://openalex.org/W3135697610","https://openalex.org/W2522183581","https://openalex.org/W2954371137"],"abstract_inverted_index":{"Currently,":[0],"medical":[1,9,66,94,102,119,126,159],"vision":[2,10,67],"language":[3,68],"models":[4,16],"are":[5,17,178],"widely":[6],"used":[7],"in":[8,38,55,104,117,181,189],"question":[11,145],"answering":[12,146],"tasks.":[13,161],"However,":[14],"existing":[15],"confronted":[18],"with":[19,52,71,147],"two":[20],"issues:":[21],"for":[22,41],"input,":[23],"the":[24,39,43,56,108,112,118],"model":[25,44,69],"only":[26,45,84],"relies":[27],"on":[28,156],"text":[29,47],"instructions":[30,90],"and":[31,49,76,88,96,143,150,173],"lacks":[32,50],"direct":[33],"understanding":[34],"of":[35,114],"visual":[36,72,86,171],"clues":[37,87],"image;":[40],"output,":[42],"gives":[46],"answers":[48],"connection":[51],"key":[53],"areas":[54],"image.":[57,109],"To":[58,110],"address":[59],"these":[60],"issues,":[61],"we":[62,121],"propose":[63,122],"a":[64,124],"unified":[65],"MIMO,":[70],"referring":[73,172],"Multimodal":[74,79],"Input":[75],"pixel":[77,174],"grounding":[78,175],"Output.":[80],"MIMO":[81,167],"can":[82,99,168,186],"not":[83,179],"combine":[85,170],"textual":[89,105],"to":[91],"understand":[92],"complex":[93,144],"images":[95],"semantics,":[97],"but":[98],"also":[100],"ground":[101],"terminologies":[103],"output":[106],"within":[107],"overcome":[111],"scarcity":[113],"relevant":[115],"data":[116],"field,":[120],"MIMOSeg,":[123],"comprehensive":[125],"multimodal":[127,148,151,160],"dataset":[128],"including":[129],"895K":[130],"samples.":[131],"MIMOSeg":[132],"is":[133],"constructed":[134],"from":[135],"four":[136],"different":[137],"perspectives,":[138],"covering":[139],"basic":[140],"instruction":[141],"following":[142],"input":[149],"output.":[152],"We":[153],"conduct":[154],"experiments":[155],"several":[157],"downstream":[158],"Extensive":[162],"experimental":[163],"results":[164],"verify":[165],"that":[166],"uniquely":[169],"capabilities,":[176],"which":[177],"available":[180],"previous":[182],"models.":[183],"Our":[184],"project":[185],"be":[187],"found":[188],"https://github.com/pkusixspace/MIMO.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
