{"id":"https://openalex.org/W7220694551","doi":"https://doi.org/10.48550/arxiv.2610.05996","title":"EpicWorldModel: Exploration-driven Planning with Latent World Models","display_name":"EpicWorldModel: Exploration-driven Planning with Latent World Models","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220694551","doi":"https://doi.org/10.48550/arxiv.2610.05996"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05996","pdf_url":"https://arxiv.org/pdf/2610.05996","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":null,"license_id":null,"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/2610.05996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157693081","display_name":"Bowen Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Bowen","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085140402","display_name":"Julian Ost","orcid":"https://orcid.org/0000-0001-6860-0246","observed_orcids":["https://orcid.org/0000-0001-6860-0246"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ost, Julian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157697708","display_name":"May Mei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei, May","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792178","display_name":"Anirudha Majumdar","orcid":"https://orcid.org/0009-0002-2296-7485","observed_orcids":["https://orcid.org/0009-0002-2296-7485","https://orcid.org/0000-0002-9383-6071"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majumdar, Anirudha","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059313827","display_name":"Felix Heide","orcid":"https://orcid.org/0000-0002-8054-9823","observed_orcids":["https://orcid.org/0000-0002-8054-9823"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heide, Felix","raw_affiliation_strings":["Princeton University","Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Torc Robotics","institution_ids":["https://openalex.org/I4210124078"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.98580002784729,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.98580002784729,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.01080000028014183,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.00039999998989515007,"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/latent-world-models","display_name":"latent world models","score":0.9900000095367432},{"id":"https://openalex.org/keywords/jepa","display_name":"JEPA","score":0.8799999952316284},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.6740000247955322},{"id":"https://openalex.org/keywords/partially-observable-environments","display_name":"partially observable environments","score":0.8090000152587891},{"id":"https://openalex.org/keywords/occlusion","display_name":"occlusion","score":0.9139999747276306},{"id":"https://openalex.org/keywords/forecast-uncertainty","display_name":"forecast uncertainty","score":0.5099999904632568},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"cross-entropy method","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6126999855041504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315999984741211},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05996","pdf_url":"https://arxiv.org/pdf/2610.05996","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.05996","doi":"https://doi.org/10.48550/arxiv.2610.05996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05996","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.05996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05996","pdf_url":"https://arxiv.org/pdf/2610.05996","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":null,"license_id":null,"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/W7220694551.pdf","grobid_xml":"https://content.openalex.org/works/W7220694551.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1872312298","https://openalex.org/W2795843265","https://openalex.org/W3205794883","https://openalex.org/W4297676498","https://openalex.org/W4303647933","https://openalex.org/W4309799367","https://openalex.org/W4319050105","https://openalex.org/W4367832869","https://openalex.org/W4385261898","https://openalex.org/W4394652010","https://openalex.org/W4394861491","https://openalex.org/W4403928888","https://openalex.org/W4406052102","https://openalex.org/W4409092337","https://openalex.org/W4409147637","https://openalex.org/W4414079054","https://openalex.org/W4415273528","https://openalex.org/W4416338927","https://openalex.org/W4416981842","https://openalex.org/W4417136857","https://openalex.org/W4417261359","https://openalex.org/W6891880838","https://openalex.org/W6910795718","https://openalex.org/W7101444818","https://openalex.org/W7125496427","https://openalex.org/W7126064400","https://openalex.org/W7126185702","https://openalex.org/W7140141371","https://openalex.org/W7160076956"],"related_works":["https://openalex.org/W7171663849","https://openalex.org/W7214711741","https://openalex.org/W7163058980","https://openalex.org/W7160855100","https://openalex.org/W7166853236","https://openalex.org/W7214783055","https://openalex.org/W7166007562","https://openalex.org/W7223126082","https://openalex.org/W7214719230","https://openalex.org/W7204500055"],"abstract_inverted_index":{"Latent":[0],"world":[1],"models":[2],"based":[3],"on":[4,104],"Joint-Embedding":[5],"Predictive":[6],"Architecture":[7],"(JEPA)":[8],"are":[9,137],"deterministic":[10],"by":[11,97],"design.":[12],"While":[13],"successful":[14],"in":[15,170],"fully":[16],"observable":[17],"scenarios,":[18],"this":[19,117],"paradigm":[20],"breaks":[21],"down":[22],"when":[23,79],"past":[24],"observations":[25],"and":[26,49],"actions":[27],"lead":[28],"to":[29,36,43,68,100,140,166],"multiple":[30,71],"plausible":[31],"future":[32,73],"possibilities,":[33],"e.g.,":[34],"due":[35],"occlusion.":[37],"We":[38,57,90,143],"introduce":[39],"EpicWorldModel,":[40],"a":[41,76,109,150],"framework":[42],"train":[44,59],"stochastic":[45],"JEPAs":[46],"for":[47,113],"environments":[48],"tasks":[50],"with":[51,63,129,156],"inherent":[52],"uncertainty":[53,118],"under":[54],"partially":[55],"observability.":[56],"jointly":[58],"the":[60,80,87,145,157],"EpicWorldModel":[61,148],"predictor":[62],"its":[64,98],"latent":[65,153],"representation":[66],"space":[67],"directly":[69],"predict":[70],"potential":[72],"states":[74],"using":[75],"flow-matching":[77],"objective,":[78],"goal-relevant":[81],"scene":[82],"content":[83],"is":[84],"absent":[85],"from":[86],"conditioning":[88],"history.":[89],"show":[91],"that":[92],"flow":[93],"predictive":[94,105],"variance,":[95],"motivated":[96],"relation":[99],"an":[101],"upper":[102],"bound":[103],"entropy,":[106],"serves":[107],"as":[108],"useful":[110],"exploration":[111,130],"guidance":[112],"planning.":[114],"By":[115],"incorporating":[116],"signal":[119],"into":[120],"Cross-Entropy":[121],"Method":[122],"(CEM)-based":[123],"planning,":[124],"our":[125],"approach":[126],"balances":[127],"goal-reaching":[128],"of":[131,147,152],"uncertain":[132],"regions":[133],"where":[134],"occluded":[135],"goals":[136],"most":[138],"likely":[139],"be":[141],"located.":[142],"demonstrate":[144],"effectiveness":[146],"through":[149],"series":[151],"planning":[154],"experiments":[155],"best":[158],"or":[159],"on-par":[160],"performance":[161],"across":[162],"tasks,":[163],"showing":[164],"up":[165],"22%":[167],"empirical":[168],"improvement":[169],"success":[171],"rate":[172],"over":[173],"LeWorldModel.":[174]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}