{"id":"https://openalex.org/W7138225472","doi":"https://doi.org/10.1609/aaai.v40i24.39079","title":"Enhancing Medical Large Vision-Language Models via Alignment Distillation","display_name":"Enhancing Medical Large Vision-Language Models via Alignment Distillation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138225472","doi":"https://doi.org/10.1609/aaai.v40i24.39079"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i24.39079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39079","pdf_url":null,"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://doi.org/10.1609/aaai.v40i24.39079","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102622763","display_name":"Aofei Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aofei Chang","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698952","display_name":"Ting Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["State University of New York at Stony Brook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Stony Brook","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129661445","display_name":"Fenglong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fenglong Ma","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"24","first_page":"19952","last_page":"19960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9861000180244446,"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":0.9861000180244446,"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":0.0071000000461936,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0010999999940395355,"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/hallucinating","display_name":"Hallucinating","score":0.9172000288963318},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6220999956130981},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48510000109672546},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4327000081539154}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9172000288963318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7063000202178955},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202000141143799},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5174000263214111},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4327000081539154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i24.39079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39079","pdf_url":null,"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/39079","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39079","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.v40i24.39079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i24.39079","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"Large":[1],"Vision-Language":[2],"Models":[3],"(Med-LVLMs)":[4],"have":[5],"shown":[6],"promising":[7],"results":[8],"in":[9],"clinical":[10],"applications,":[11],"but":[12],"often":[13],"suffer":[14],"from":[15,62],"hallucinated":[16],"outputs":[17],"due":[18],"to":[19,32,70],"misaligned":[20],"visual":[21,36,41,59,79,84,108],"understanding.":[22],"In":[23],"this":[24,33],"work,":[25],"we":[26,48],"identify":[27],"two":[28,74],"fundamental":[29],"limitations":[30],"contributing":[31],"issue:":[34],"insufficient":[35],"representation":[37],"learning":[38],"and":[39,88,106,120],"poor":[40],"attention":[42,95],"alignment.":[43],"To":[44],"address":[45],"these":[46],"problems,":[47],"propose":[49],"MedAlign,":[50],"a":[51,63,77],"simple,":[52],"lightweight":[53],"alignment":[54,60,80],"distillation":[55,75,91],"framework":[56],"that":[57,93,114],"transfers":[58],"knowledge":[61],"domain-specific":[64],"Contrastive":[65],"Language-Image":[66],"Pre-training":[67],"(CLIP)":[68],"model":[69],"Med-LVLMs.":[71],"MedAlign":[72,115],"introduces":[73],"losses:":[76],"spatial-aware":[78],"loss":[81,92],"based":[82],"on":[83,102],"token-level":[85],"similarity":[86],"structures,":[87],"an":[89],"attention-aware":[90],"guides":[94],"toward":[96],"diagnostically":[97],"relevant":[98],"regions.":[99],"Extensive":[100],"experiments":[101],"medical":[103,107],"report":[104],"generation":[105],"question":[109],"answering":[110],"(VQA)":[111],"benchmarks":[112],"show":[113],"consistently":[116],"improves":[117],"both":[118],"performance":[119],"interpretability,":[121],"yielding":[122],"more":[123],"visually":[124],"grounded":[125],"outputs.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-18T00:00:00"}