{"id":"https://openalex.org/W7162544936","doi":"https://doi.org/10.48550/arxiv.2605.26353","title":"Personalized Generative Models for Contextual Debiasing","display_name":"Personalized Generative Models for Contextual Debiasing","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162544936","doi":"https://doi.org/10.48550/arxiv.2605.26353"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26353","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137160153","display_name":"Xinran Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Xinran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137166711","display_name":"Esin Tureci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tureci, Esin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137104907","display_name":"Prachi Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sinha, Prachi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137108413","display_name":"Ye Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073539430","display_name":"V. Ramaswamy","orcid":"https://orcid.org/0000-0002-0552-5338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramaswamy, Vikram V.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137180076","display_name":"Olga Russakovsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Russakovsky, Olga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9404000043869019,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9404000043869019,"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":0.01360000018030405,"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/T11448","display_name":"Face recognition and analysis","score":0.010599999688565731,"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/debiasing","display_name":"Debiasing","score":0.5490999817848206},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5200999975204468},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5199000239372253},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.37450000643730164},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3456999957561493},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.33000001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6707000136375427},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33000001311302185},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26353","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26353","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Different":[0],"visual":[1,144],"patterns":[2],"appear":[3,13],"with":[4,86,114,122,138,157],"different":[5],"frequencies":[6],"in":[7,28,41,74],"the":[8,75,106,158,170],"world:":[9],"e.g.,":[10],"beach":[11,47],"balls":[12],"on":[14,21,49,61,177,183],"sand":[15],"more":[16,37,56],"often":[17],"than":[18,58],"they":[19],"do":[20],"a":[22,33,46,50,125],"road.":[23],"These":[24],"statistics":[25],"are":[26],"reflected":[27],"vision":[29],"datasets,":[30],"and":[31,153,180,195],"as":[32,92],"result":[34],"trained":[35],"models":[36,131],"easily":[38],"recognize":[39],"objects":[40],"common":[42],"scenarios.":[43],"However,":[44],"recognizing":[45,59],"ball":[48],"road":[51],"may":[52,78],"arguably":[53],"be":[54,79],"even":[55],"important":[57],"it":[60],"sand.":[62],"We":[63,117,161,173],"study":[64],"how":[65],"to":[66,102,105,132,166],"mitigate":[67],"this":[68],"discrepancy.":[69],"Since":[70],"collecting":[71],"uncommon":[72,115],"images":[73,85,113,137,148],"real":[76],"world":[77],"difficult,":[80],"we":[81],"explore":[82],"whether":[83],"generating":[84],"less":[87],"frequent":[88],"contexts":[89,140],"can":[90],"serve":[91],"effective":[93],"training":[94],"augmentation.":[95],"A":[96],"key":[97],"challenge":[98],"is":[99],"guiding":[100],"generations":[101],"remain":[103,154],"close":[104],"original":[107,143,159],"dataset":[108],"distribution":[109],"while":[110,141],"creating":[111],"diverse":[112],"contexts.":[116],"introduce":[118],"Decoupling":[119],"Contextual":[120],"Patterns":[121],"Generations":[123],"(DecoupleGen),":[124],"method":[126],"that":[127],"personalizes":[128],"text-to-image":[129],"diffusion":[130],"facilitate":[133],"coherent":[134],"synthesis":[135],"of":[136,169],"rare":[139],"preserving":[142],"details.":[145],"The":[146],"generated":[147],"contain":[149],"semantically":[150],"meaningful":[151],"content":[152],"visually":[155],"aligned":[156],"datasets.":[160,186],"further":[162],"apply":[163],"verification":[164],"constraints":[165],"ensure":[167],"relevance":[168],"augmented":[171],"data.":[172],"evaluate":[174],"our":[175,196],"approach":[176],"object":[178],"classification":[179],"recognition":[181],"tasks":[182],"complex":[184],"scene":[185],"Our":[187],"experiments":[188],"demonstrate":[189],"consistent":[190],"improvements":[191],"over":[192],"previous":[193],"approaches,":[194],"analyses":[197],"identify":[198],"factors":[199],"underlying":[200],"these":[201],"improvements.":[202]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-28T00:00:00"}