{"id":"https://openalex.org/W7137927450","doi":"https://doi.org/10.1609/aaai.v40i8.37517","title":"Versatile Vision-Language Model for 3D Computed Tomography","display_name":"Versatile Vision-Language Model for 3D Computed Tomography","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137927450","doi":"https://doi.org/10.1609/aaai.v40i8.37517"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37517","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37517","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37517/41479","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37517/41479","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088505320","display_name":"Jiayu Lei","orcid":"https://orcid.org/0000-0002-0484-5380"},"institutions":[{"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":"Jiayu Lei","raw_affiliation_strings":["University of Science and Technology of China, Anhui, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Anhui, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129731882","display_name":"Ziqing Fan","orcid":null},"institutions":[{"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":"Ziqing Fan","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129665768","display_name":"Yanyong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Yanyong Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nInstitute of Artificial Intelligence for Medicine, School of Medicine, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nInstitute of Artificial Intelligence for Medicine, School of Medicine, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"institutions":[{"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":"Weidi Xie","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746352","display_name":"Ya Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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":"Ya Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nInstitute of Artificial Intelligence for Medicine, School of Medicine, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nInstitute of Artificial Intelligence for Medicine, School of Medicine, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129679332","display_name":"Yanfeng Wang","orcid":null},"institutions":[{"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":"Yanfeng Wang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China\nShanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"5945","last_page":"5954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5788999795913696,"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":0.5788999795913696,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1526000052690506,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.10570000112056732,"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/leverage","display_name":"Leverage (statistics)","score":0.7002000212669373},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6294999718666077},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44609999656677246},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4138999879360199},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41130000352859497},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483000159263611},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6294999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497999787330627},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2678000032901764}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37517","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37517","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37517/41479","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37517","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37517","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37517","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37517/41479","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.681174099445343,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137927450.pdf","grobid_xml":"https://content.openalex.org/works/W7137927450.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Representation":[0],"learning":[1,187],"serves":[2],"as":[3,40],"a":[4,31,49,139,143,181],"foundational":[5],"component":[6],"of":[7,86,124],"medical":[8,170,189],"vision-language":[9,149],"models":[10,26],"(MVLMs),":[11],"enabling":[12],"cross-modal":[13],"alignment,":[14],"semantic":[15],"consistency,":[16],"and":[17,45,55,77,98,156,165],"enhanced":[18],"generalization":[19],"capabilities":[20],"for":[21,103,151,168,184],"downstream":[22,37,93,130],"tasks.":[23,131],"As":[24],"generalist":[25],"rapidly":[27],"evolve,":[28],"there":[29,82],"is":[30],"pressing":[32],"need":[33],"to":[34,69],"unify":[35],"diverse":[36,78],"tasks,":[38,101],"such":[39],"diagnosis,":[41,96],"segmentation,":[42,97],"report":[43],"generation,":[44],"multiple":[46],"choice":[47],"within":[48],"cohesive":[50],"framework,":[51],"demanding":[52],"more":[53],"efficient":[54,87,152],"versatile":[56],"visual":[57],"representation":[58],"learning.":[59],"However,":[60],"current":[61,111],"MVLMs":[62,112],"predominately":[63],"follow":[64],"CLIP-style":[65],"vision":[66,88],"pretraining,":[67],"failing":[68],"leverage":[70],"heterogeneous":[71,153],"data":[72,154],"resources":[73],"with":[74,147],"multi-dimensional":[75],"imaging":[76,105],"annotation":[79],"forms.":[80],"And":[81],"lacks":[83],"systematic":[84],"analysis":[85],"encoder":[89,146],"design":[90],"across":[91,128,176],"varied":[92],"applications,":[94],"including":[95],"text":[99],"generation":[100],"particularly":[102],"volumetric":[104,169],"like":[106],"Computed":[107],"Tomography":[108],"(CT).":[109],"Besides,":[110],"exhibit":[113],"constrained":[114],"voxel-level":[115,166],"capabilities,":[116],"lacking":[117],"effective":[118],"multi-task":[119],"instruction":[120,158],"tuning":[121,159],"framework":[122],"capable":[123],"achieving":[125],"robust":[126],"performance":[127,175],"various":[129],"To":[132],"address":[133],"these":[134],"challenges,":[135],"we":[136],"propose":[137],"CTInstruct,":[138],"novel":[140],"MVLM":[141],"employing":[142],"hybrid":[144],"ResNet-ViT":[145],"multi-granular":[148],"pretraining":[150],"modeling,":[155],"unified":[157],"that":[160],"jointly":[161],"optimizes":[162],"discriminative,":[163],"generative,":[164],"reasoning":[167],"imaging.":[171,190],"CTInstruct":[172],"achieves":[173],"SOTA":[174],"8":[177],"CT":[178],"benchmarks,":[179],"setting":[180],"new":[182],"standard":[183],"data-efficient":[185],"multimodal":[186],"in":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}