{"id":"https://openalex.org/W7165383846","doi":"https://doi.org/10.1016/j.patcog.2026.114283","title":"Fine-grained alignment in medical pathology vision-language models via variational distillation","display_name":"Fine-grained alignment in medical pathology vision-language models via variational distillation","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165383846","doi":"https://doi.org/10.1016/j.patcog.2026.114283"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.114283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.114283","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.114283","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108826321","display_name":"Runlin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal-Hong Kong Baptist University","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Runlin Huang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China","Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004789363","display_name":"Haowei Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal-Hong Kong Baptist University","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haowei Lin","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China","Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075676776","display_name":"Weipeng Zhuo","orcid":"https://orcid.org/0000-0002-1810-7071"},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal-Hong Kong Baptist University","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Weipeng Zhuo","raw_affiliation_strings":["Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139014193","display_name":"Yiu-ming Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-ming Cheung","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139025543","display_name":"Hongmin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Cai","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Wushan, Guangzhou, 510006, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Wushan, Guangzhou, 510006, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060723223","display_name":"Weifeng Su","orcid":"https://orcid.org/0000-0001-9501-0321"},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal-Hong Kong Baptist University","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Weifeng Su","raw_affiliation_strings":["Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9501-0321","affiliations":[{"raw_affiliation_string":"Division of Science and Technology, Beijing Normal\u2013Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University, Zhuhai, 519087, Guangdong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060723223"],"corresponding_institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":{"value":2710,"currency":"USD","value_usd":2710},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80209748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"180","issue":null,"first_page":"114283","last_page":"114283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.41620001196861267,"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":0.41620001196861267,"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":0.20229999721050262,"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/T10862","display_name":"AI in cancer detection","score":0.13650000095367432,"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/ambiguity","display_name":"Ambiguity","score":0.682699978351593},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6600000262260437},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5055000185966492},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.491100013256073},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.39629998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765999972820282},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5960000157356262},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4440999925136566},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.114283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.114283","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.114283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.114283","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899635195732117,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2435090885","https://openalex.org/W3198377975","https://openalex.org/W4317436377","https://openalex.org/W4408103032","https://openalex.org/W4408389450","https://openalex.org/W4409198978","https://openalex.org/W4410702876","https://openalex.org/W4413145524","https://openalex.org/W4416239686"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"vision-language":[1],"(V-L)":[2],"models":[3,61],"exhibit":[4],"promising":[5],"performance":[6],"across":[7,35,186],"various":[8],"general-domain":[9],"tasks.":[10],"However,":[11],"they":[12],"fall":[13],"short":[14],"in":[15,152],"medical":[16],"pathology":[17,153,184],"due":[18,42],"to":[19,43,51,120,129,138,147],"the":[20,49,136,159,199,204],"critical":[21,151],"need":[22],"for":[23,30,87],"fine-grained":[24,78],"semantic":[25,104,122,149],"alignment,":[26,79,158],"which":[27],"is":[28,39],"essential":[29],"distinguishing":[31],"subtle":[32,148],"visual":[33],"patterns":[34],"categories.":[36],"This":[37,92,134],"limitation":[38],"not":[40],"merely":[41],"domain":[44],"gaps":[45],"but":[46],"stems":[47],"from":[48,106],"inability":[50],"capture":[52],"detailed,":[53],"pathology-specific":[54],"semantics.":[55],"Previous":[56],"efforts":[57],"leveraging":[58],"large":[59],"language":[60],"(LLMs)":[62],"or":[63,69],"cross-modal":[64,157],"training":[65],"often":[66],"introduce":[67],"redundant":[68],"ambiguous":[70],"cues,":[71],"ultimately":[72],"weakening":[73],"generalization.":[74],"To":[75],"explicitly":[76],"enhance":[77],"we":[80,115],"propose":[81],"a":[82,95,126],"Variational":[83],"Distillation":[84],"framework":[85],"tailored":[86],"Medical":[88],"Pathology":[89],"V-L":[90],"models.":[91],"method":[93,161,201],"introduces":[94],"dual-loop":[96],"optimization":[97],"mechanism":[98],"that":[99,198],"jointly":[100],"distills":[101],"and":[102,110,124,141,170,176,194],"aligns":[103],"signals":[105],"both":[107],"textual":[108],"inputs":[109],"external":[111],"LLM":[112],"knowledge.":[113],"Specifically,":[114],"use":[116],"variational":[117],"latent":[118],"distributions":[119],"model":[121,137],"ambiguity":[123],"apply":[125],"KL-based":[127],"loss":[128],"reduce":[130],"differences":[131],"between":[132],"signals.":[133],"encourages":[135],"retain":[139],"robust":[140],"generalizable":[142],"features,":[143],"enabling":[144],"improved":[145],"sensitivity":[146],"variations":[150],"image":[154],"understanding.":[155],"During":[156],"proposed":[160,200],"further":[162],"amplifies":[163],"modality-shared":[164],"semantics":[165],"while":[166],"suppressing":[167],"modality-specific":[168],"noise":[169],"task-irrelevant":[171],"factors,":[172],"yielding":[173],"more":[174],"precise":[175],"pathology-aware":[177],"image-text":[178],"matching.":[179],"Extensive":[180],"experiments":[181],"on":[182],"five":[183],"benchmarks":[185],"three":[187],"settings,":[188],"including":[189],"class":[190],"generalization,":[191],"few-shot":[192],"learning,":[193],"cross-organ":[195],"transfer,":[196],"demonstrate":[197],"consistently":[202],"outperforms":[203],"existing":[205],"approaches.":[206]},"counts_by_year":[],"updated_date":"2026-06-26T06:17:10.115597","created_date":"2026-06-20T00:00:00"}
