{"id":"https://openalex.org/W7106804060","doi":"https://doi.org/10.48550/arxiv.2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","display_name":"Personalized Reward Modeling for Text-to-Image Generation","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W7106804060","doi":"https://doi.org/10.48550/arxiv.2511.19458"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.19458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.19458","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"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":"https://doi.org/10.48550/arxiv.2511.19458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lee, Jeongeun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lee, Jeongeun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Heo, Ryang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heo, Ryang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Lee, Dongha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Dongha","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.4223000109195709,"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":0.4223000109195709,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2175000011920929,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.09570000320672989,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7857999801635742},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5562999844551086},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.454800009727478},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.40209999680519104},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.3935999870300293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922000288963318},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7857999801635742},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48669999837875366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.3935999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.19458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.19458","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.19458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.19458","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"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":{"Recent":[0],"text-to-image":[1],"(T2I)":[2],"models":[3],"generate":[4],"semantically":[5],"coherent":[6],"images":[7,63,110],"from":[8],"textual":[9],"prompts,":[10],"yet":[11],"evaluating":[12],"how":[13],"well":[14],"they":[15],"align":[16],"with":[17],"individual":[18,112],"user":[19,72,88],"preferences":[20],"remains":[21],"an":[22],"open":[23],"challenge.":[24],"Conventional":[25],"evaluation":[26,59,151],"methods,":[27],"general":[28],"reward":[29,53],"functions":[30],"or":[31],"similarity-based":[32],"metrics,":[33],"fail":[34],"to":[35,85],"capture":[36],"the":[37,69],"diversity":[38],"and":[39,61,111,140,145,152],"complexity":[40],"of":[41,71,126],"personal":[42],"visual":[43,124],"tastes.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"present":[49],"PIGReward,":[50],"a":[51,76,118,143,161],"personalized":[52,99,149],"model":[54],"that":[55,79,101,132],"dynamically":[56],"generates":[57],"user-conditioned":[58],"dimensions":[60],"assesses":[62],"through":[64],"CoT":[65],"reasoning.":[66],"To":[67],"address":[68],"scarcity":[70],"data,":[73],"PIGReward":[74,97,133,159],"adopt":[75],"self-bootstrapping":[77],"strategy":[78],"reasons":[80],"over":[81],"limited":[82],"reference":[83],"data":[84],"construct":[86],"rich":[87],"contexts,":[89],"enabling":[90],"personalization":[91],"without":[92],"user-specific":[93,103],"training.":[94],"Beyond":[95],"evaluation,":[96],"provides":[98],"feedback":[100],"drives":[102],"prompt":[104],"optimization,":[105],"improving":[106],"alignment":[107],"between":[108],"generated":[109],"intent.":[113],"We":[114],"further":[115],"introduce":[116],"PIGBench,":[117],"per-user":[119],"preference":[120],"benchmark":[121],"capturing":[122],"diverse":[123],"interpretations":[125],"shared":[127],"prompts.":[128],"Extensive":[129],"experiments":[130],"demonstrate":[131],"surpasses":[134],"existing":[135],"methods":[136],"in":[137],"both":[138],"accuracy":[139],"interpretability,":[141],"establishing":[142],"scalable":[144],"reasoning-based":[146],"foundation":[147],"for":[148],"T2I":[150,166],"optimization.":[153],"Taken":[154],"together,":[155],"our":[156],"findings":[157],"highlight":[158],"as":[160],"robust":[162],"steptoward":[163],"individually":[164],"aligned":[165],"generation.":[167]},"counts_by_year":[],"updated_date":"2025-11-28T02:12:24.556248","created_date":"2025-11-28T00:00:00"}