{"id":"https://openalex.org/W4415101279","doi":"https://doi.org/10.1109/wacv61042.2026.00072","title":"Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation","display_name":"Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415101279","doi":"https://doi.org/10.1109/wacv61042.2026.00072"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.08906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657345","display_name":"Xiwen Chen","orcid":"https://orcid.org/0000-0003-0170-4459"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiwen Chen","raw_affiliation_strings":["Morgan Stanley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Morgan Stanley","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439574","display_name":"Wenhui Zhu","orcid":"https://orcid.org/0009-0000-5207-6283"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhui Zhu","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058590658","display_name":"Peijie Qiu","orcid":"https://orcid.org/0000-0002-1591-5436"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peijie Qiu","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599817","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-0896-080X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Clemson University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721217","display_name":"Huayu Li","orcid":"https://orcid.org/0009-0009-7855-3522"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huayu Li","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026177673","display_name":"Haiyu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyu Wu","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002543602","display_name":"Aristeidis Sotiras","orcid":"https://orcid.org/0000-0003-0795-8820"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aristeidis Sotiras","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740828","display_name":"Yalin Wang","orcid":"https://orcid.org/0000-0002-6241-735X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yalin Wang","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011987346","display_name":"Abolfazl Razi","orcid":"https://orcid.org/0000-0002-3330-6132"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abolfazl Razi","raw_affiliation_strings":["Clemson University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100657345"],"corresponding_institution_ids":["https://openalex.org/I2802755631"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00598279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"667","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9896000027656555,"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":0.9896000027656555,"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/T10028","display_name":"Topic Modeling","score":0.9325000047683716,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9251000285148621,"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/overfitting","display_name":"Overfitting","score":0.7595999836921692},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.536300003528595},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.474700003862381},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4657999873161316},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.46149998903274536},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4426000118255615}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7595999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064000129699707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5598999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.37720000743865967},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2721000015735626}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.08906","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08906","pdf_url":"https://arxiv.org/pdf/2503.08906","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08906","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:oai:arXiv.org:2503.08906","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08906","pdf_url":"https://arxiv.org/pdf/2503.08906","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"such":[3],"as":[4,20],"CLIP":[5],"demonstrate":[6,121],"strong":[7],"performance":[8],"but":[9],"struggle":[10],"when":[11],"adapted":[12],"to":[13,26,39],"downstream":[14],"tasks.":[15],"Prompt":[16],"learning":[17,56,131],"has":[18],"emerged":[19],"an":[21,51],"efficient":[22],"and":[23,41,71,83,98,108,138],"effective":[24,126],"strategy":[25],"adapt":[27],"VLMs":[28],"while":[29],"preserving":[30,62],"their":[31],"pre-trained":[32,70],"knowledge.":[33],"However,":[34],"existing":[35,129],"methods":[36],"still":[37],"lead":[38],"overfitting":[40],"degrade":[42],"zero-shot":[43],"generalization.":[44,99],"To":[45],"address":[46],"this":[47],"challenge,":[48],"we":[49],"propose":[50],"optimal":[52],"transport":[53],"(OT)-guided":[54],"prompt":[55,90,130],"framework":[57],"that":[58,122],"mitigates":[59],"forgetting":[60],"by":[61],"the":[63,85],"structural":[64],"consistency":[65],"of":[66],"feature":[67,114],"distributions":[68],"between":[69,96],"fine-tuned":[72],"models.":[73],"Unlike":[74],"conventional":[75],"point-wise":[76],"constraints,":[77],"OT":[78],"naturally":[79],"captures":[80],"cross-instance":[81],"relationships":[82],"expands":[84],"feasible":[86],"parameter":[87],"space":[88],"for":[89],"tuning,":[91],"allowing":[92],"a":[93,112],"better":[94],"tradeoff":[95],"adaptation":[97],"Our":[100],"approach":[101],"enforces":[102],"joint":[103],"constraints":[104],"on":[105,118],"both":[106],"vision":[107],"text":[109],"representations,":[110],"ensuring":[111],"holistic":[113],"alignment.":[115],"Extensive":[116],"experiments":[117],"benchmark":[119],"datasets":[120],"our":[123],"simple":[124],"yet":[125],"method":[127],"outperforms":[128],"strategies":[132],"in":[133],"base-to-novel":[134],"generalization,":[135,140],"cross-dataset":[136],"evaluation,":[137],"domain":[139],"without":[141],"requiring":[142],"additional":[143],"augmentation":[144],"or":[145],"ensemble":[146],"techniques.":[147]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-13T00:00:00"}