{"id":"https://openalex.org/W7130726485","doi":"https://doi.org/10.48550/arxiv.2602.17535","title":"LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs","display_name":"LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs","publication_year":2026,"publication_date":"2026-02-19","ids":{"openalex":"https://openalex.org/W7130726485","doi":"https://doi.org/10.48550/arxiv.2602.17535"},"language":"en","primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.17535","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058274549","display_name":"Behzad Bozorgtabar","orcid":"https://orcid.org/0000-0002-5759-4896"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bozorgtabar, Behzad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126523874","display_name":"Dwarikanath Mahapatra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahapatra, Dwarikanath","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126491061","display_name":"Sudipta Roy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy, Sudipta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126448626","display_name":"Muzammal Naseer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naseer, Muzammal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121288446","display_name":"Imran Razzak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Razzak, Imran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126484499","display_name":"Zongyuan Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zongyuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058274549"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5953999757766724,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5953999757766724,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08510000258684158,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06459999829530716,"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/calibration","display_name":"Calibration","score":0.6658999919891357},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/conformal-map","display_name":"Conformal map","score":0.512499988079071},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5062000155448914},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/sequential-analysis","display_name":"Sequential analysis","score":0.46219998598098755}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583999991416931},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187000036239624},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4973999857902527},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.41119998693466187},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C15152581","wikidata":"https://www.wikidata.org/wiki/Q7833966","display_name":"Transduction (biophysics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775999903678894},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26579999923706055}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.17535","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:publications/a6770dae-994f-40f8-8da6-d14c40efa4b0","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/a6770dae-994f-40f8-8da6-d14c40efa4b0","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bozorgtabar, B, Mahapatra, D, Roy , S, Naseer, M, Razzak, I & Ge, Z 2026, LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. < https://arxiv.org/pdf/2602.17535 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.48550/arxiv.2602.17535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.17535","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.17535","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"vision-language":[1,117],"models":[2],"(VLMs)":[3],"are":[4],"strong":[5],"zero-shot":[6,84,217],"recognizers":[7],"for":[8],"medical":[9,173],"imaging,":[10],"but":[11],"their":[12],"reliability":[13],"under":[14],"domain":[15],"shift":[16],"hinges":[17],"on":[18,75],"calibrated":[19],"uncertainty":[20,118],"with":[21],"guarantees.":[22,61],"Split":[23],"conformal":[24,111],"prediction":[25,31,129],"(SCP)":[26],"offers":[27],"finite-sample":[28],"coverage,":[29,191],"yet":[30],"sets":[32],"often":[33],"become":[34],"large":[35],"(low":[36],"efficiency)":[37],"and":[38,59,70,79,124,132,149,175,184,196,210],"class-wise":[39,133],"coverage":[40,43],"unbalanced-high":[41],"class-conditioned":[42],"gap":[44,199],"(CCV),":[45],"especially":[46],"in":[47,163],"few-shot,":[48],"imbalanced":[49],"regimes;":[50],"moreover,":[51],"naively":[52],"adapting":[53],"to":[54,127,200],"calibration":[55,78,168],"labels":[56],"breaks":[57],"exchangeability":[58],"voids":[60],"We":[62,106],"propose":[63],"\\texttt{\\textbf{LATA}}":[64,138,179,215],"(Laplacian-Assisted":[65],"Transductive":[66],"Adaptation),":[67],"a":[68,92,103,109,164],"\\textit{training-":[69],"label-free}":[71],"refinement":[72],"that":[73,113,155,214],"operates":[74],"the":[76,116,198],"joint":[77],"test":[80],"pool":[81],"by":[82],"smoothing":[83],"probabilities":[85],"over":[86],"an":[87,151],"image-image":[88],"k-NN":[89],"graph":[90],"using":[91,167,204],"small":[93],"number":[94],"of":[95],"CCCP":[96],"mean-field":[97],"updates,":[98],"preserving":[99],"SCP":[100],"validity":[101],"via":[102],"deterministic":[104],"transform.":[105],"further":[107],"introduce":[108],"\\textit{failure-aware}":[110],"score":[112],"plugs":[114],"into":[115],"(ViLU)":[119],"framework,":[120],"providing":[121],"instance-level":[122],"difficulty":[123],"label":[125],"plausibility":[126],"improve":[128],"set":[130,182],"efficiency":[131],"balance":[134],"at":[135],"fixed":[136],"coverage.":[137],"is":[139],"black-box":[140],"(no":[141],"VLM":[142],"updates),":[143],"compute-light":[144],"(windowed":[145],"transduction,":[146],"no":[147],"backprop),":[148],"includes":[150],"optional":[152],"prior":[153,193],"knob":[154],"can":[156],"run":[157],"strictly":[158],"label-free":[159],"or,":[160],"if":[161],"desired,":[162],"label-informed":[165],"variant":[166],"marginals":[169],"once.":[170],"Across":[171],"\\textbf{three}":[172],"VLMs":[174],"\\textbf{nine}":[176],"downstream":[177],"tasks,":[178],"consistently":[180],"reduces":[181],"size":[183],"CCV":[185],"while":[186,203],"matching":[187],"or":[188],"tightening":[189],"target":[190],"outperforming":[192],"transductive":[194],"baselines":[195],"narrowing":[197],"label-using":[201],"methods,":[202],"far":[205],"less":[206],"compute.":[207],"Comprehensive":[208],"ablations":[209],"qualitative":[211],"analyses":[212],"show":[213],"sharpens":[216],"predictions":[218],"without":[219],"compromising":[220],"exchangeability.":[221]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-21T00:00:00"}