{"id":"https://openalex.org/W7220710054","doi":"https://doi.org/10.48550/arxiv.2610.04920","title":"PWM: Personalized World Models with Online Reinforcement Learning","display_name":"PWM: Personalized World Models with Online Reinforcement Learning","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220710054","doi":"https://doi.org/10.48550/arxiv.2610.04920"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04920","pdf_url":"https://arxiv.org/pdf/2610.04920","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157753778","display_name":"Zhexin Lou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Zhexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157708497","display_name":"Guancheng Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Guancheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157740931","display_name":"Zeyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157731088","display_name":"Yi Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157781288","display_name":"Yang Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246","observed_orcids":["https://orcid.org/0000-0002-2077-1246","https://orcid.org/0000-0002-6973-8121"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Hao","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":true,"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":0.9829000234603882,"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":0.9829000234603882,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.010499999858438969,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.7670000195503235},{"id":"https://openalex.org/keywords/lora-adapters","display_name":"LoRA adapters","score":0.7879999876022339},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.6819999814033508},{"id":"https://openalex.org/keywords/visual-continuity","display_name":"visual continuity","score":0.4950000047683716}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8058000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371999740600586},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45649999380111694},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04920","pdf_url":"https://arxiv.org/pdf/2610.04920","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.04920","doi":"https://doi.org/10.48550/arxiv.2610.04920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04920","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.04920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04920","pdf_url":"https://arxiv.org/pdf/2610.04920","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220710054.pdf","grobid_xml":"https://content.openalex.org/works/W7220710054.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W4391631327","https://openalex.org/W4400612128","https://openalex.org/W4405721163","https://openalex.org/W4414886176","https://openalex.org/W4417517408"],"related_works":["https://openalex.org/W7128474907","https://openalex.org/W7208729455","https://openalex.org/W4399758271","https://openalex.org/W7207523118","https://openalex.org/W7162790441","https://openalex.org/W7203638886","https://openalex.org/W7164883443","https://openalex.org/W7083825619","https://openalex.org/W4415797250","https://openalex.org/W4417009953"],"abstract_inverted_index":{"Pretrained":[0],"world":[1,46],"models":[2,47],"can":[3],"generate":[4],"diverse":[5],"environments,":[6],"yet":[7],"users":[8],"often":[9],"want":[10],"to":[11,102,215],"explore":[12],"a":[13,41,82,87,108],"particular":[14],"scene":[15,50,91],"specified":[16],"by":[17],"their":[18],"own":[19],"video.":[20],"This":[21],"requires":[22],"learning":[23,136],"the":[24,30,58,72,76,103,137,176,189,216],"scene's":[25],"visual":[26,93,212],"identity":[27],"while":[28,97,209],"retaining":[29,210],"quality":[31,213],"of":[32,107,164,175],"action-conditioned":[33],"generation.":[34],"We":[35,123,140],"introduce":[36,142],"Personalized":[37],"World":[38],"Models":[39],"(PWM),":[40],"framework":[42],"for":[43,90,135],"customizing":[44],"interactive":[45],"from":[48,71],"short":[49],"videos":[51],"through":[52],"online":[53],"reinforcement":[54],"learning.":[55],"In":[56,75],"PWM,":[57],"support":[59],"trajectory":[60],"and":[61,95,120,151,161,173,201],"its":[62],"associated":[63],"controls":[64],"provide":[65],"reward":[66,89],"feedback":[67],"on":[68,156],"continuations":[69],"sampled":[70],"current":[73],"policy.":[74],"GRPO":[77,160,190],"instantiation,":[78,191],"group-relative":[79],"optimization":[80,133],"updates":[81],"compact":[83],"LoRA":[84],"adapter":[85],"using":[86],"unified":[88],"appearance,":[92],"continuity,":[94],"motion,":[96],"base-policy":[98],"anchoring":[99],"regularizes":[100],"changes":[101],"pretrained":[104,217],"generation":[105],"prior":[106],"frozen":[109],"Yume-5B":[110],"backbone.":[111],"The":[112,159],"same":[113],"adaptation":[114],"procedure":[115],"is":[116],"applied":[117],"across":[118,148,184],"real":[119],"rendered":[121],"environments.":[122],"also":[124,141],"instantiate":[125],"PWM":[126,165],"with":[127,153,180],"DiffusionNFT":[128,162],"as":[129],"an":[130],"alternative":[131],"reward-guided":[132],"method":[134],"scene-specific":[138],"adapter.":[139],"PWM-Bench,":[143],"comprising":[144],"150":[145],"customization":[146,167,199],"tasks":[147],"Indoor,":[149],"Outdoor,":[150],"Gaming,":[152],"paired":[154],"evaluation":[155],"held-out":[157],"continuations.":[158],"instantiations":[163],"improve":[166],"over":[168],"native":[169],"Yume":[170],"in":[171,206],"71.3%":[172],"65.3%":[174],"evaluated":[177],"scenes,":[178],"respectively,":[179],"positive":[181],"mean":[182,198,203],"gains":[183,200],"all":[185],"three":[186],"domains.":[187],"For":[188],"matched":[192],"SFT":[193],"comparisons":[194],"further":[195],"demonstrate":[196],"higher":[197],"better":[202],"image-quality":[204],"scores":[205],"every":[207],"domain,":[208],"frame-level":[211],"close":[214],"model.":[218]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}