{"id":"https://openalex.org/W7138336957","doi":"https://doi.org/10.1609/aaai.v40i6.42465","title":"Pre-Trained Video Generative Models as World Simulators","display_name":"Pre-Trained Video Generative Models as World Simulators","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138336957","doi":"https://doi.org/10.1609/aaai.v40i6.42465"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42465/46426","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42465/46426","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129697414","display_name":"Haoran He","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoran He","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659230","display_name":"Yang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690542","display_name":"Liang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["SUN YAT-SEN UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUN YAT-SEN UNIVERSITY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062979221","display_name":"Zhongwen Xu","orcid":"https://orcid.org/0000-0002-9348-7262"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwen Xu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129679116","display_name":"Ling Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ling Pan","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4645","last_page":"4653"},"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":0.6069999933242798,"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":0.6069999933242798,"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/T12290","display_name":"Human Motion and Animation","score":0.27900001406669617,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.018300000578165054,"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/controllability","display_name":"Controllability","score":0.5491999983787537},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4823000133037567},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4781999886035919},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4650000035762787},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3928000032901764},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4823000133037567},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.36899998784065247},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42465/46426","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172221","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172221","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42465/46426","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138336957.pdf","grobid_xml":"https://content.openalex.org/works/W7138336957.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"generative":[1,56],"models":[2,57],"pre-trained":[3,54],"on":[4,24,96],"large-scale":[5],"internet":[6],"datasets":[7],"have":[8],"achieved":[9],"remarkable":[10],"success,":[11],"excelling":[12],"at":[13],"producing":[14],"realistic":[15],"synthetic":[16],"videos.":[17],"However,":[18],"they":[19],"often":[20],"generate":[21],"clips":[22],"based":[23],"static":[25],"prompts":[26],"(e.g.,":[27],"text":[28],"or":[29],"images),":[30],"limiting":[31],"their":[32],"ability":[33],"to":[34,52,110,133,147,169,190],"model":[35,132],"interactive":[36],"and":[37,75,150,165],"dynamic":[38,104,135],"scenarios.":[39],"In":[40],"this":[41,117],"paper,":[42],"we":[43,79,100,119,186],"propose":[44,187],"Dynamic":[45],"World":[46],"Simulation":[47],"(DWS),":[48],"a":[49,81,122],"novel":[50],"approach":[51],"transform":[53],"video":[55],"into":[58,89],"controllable":[59],"world":[60,113,176],"simulators":[61],"capable":[62],"of":[63,94,173],"executing":[64],"specified":[65],"action":[66,127],"trajectories.":[67],"To":[68],"achieve":[69],"precise":[70],"alignment":[71],"between":[72],"conditioned":[73],"actions":[74],"generated":[76],"visual":[77,98],"changes,":[78],"introduce":[80,121],"lightweight,":[82],"universal":[83],"action-conditioned":[84],"module":[85],"that":[86,102,125,141],"seamlessly":[87],"integrates":[88],"any":[90],"existing":[91],"model.":[92],"Instead":[93],"focusing":[95],"complex":[97],"details,":[99],"demonstrate":[101,140],"consistent":[103,161],"transition":[105],"modeling":[106],"is":[107],"the":[108,131,171,174],"key":[109],"building":[111],"powerful":[112],"simulators.":[114],"Building":[115],"upon":[116],"insight,":[118],"further":[120],"motion-reinforced":[123],"loss":[124],"enhances":[126],"controllability":[128],"by":[129],"compelling":[130],"capture":[134],"changes":[136],"more":[137],"effectively.":[138],"Experiments":[139],"DWS":[142],"can":[143],"be":[144],"versatilely":[145],"applied":[146],"both":[148],"diffusion":[149],"autoregressive":[151],"transformer":[152],"models,":[153],"achieving":[154],"significant":[155],"improvements":[156],"in":[157,178],"generating":[158],"action-controllable,":[159],"dynamically":[160],"videos":[162],"across":[163],"games":[164],"robotics":[166],"domains.":[167],"Moreover,":[168],"facilitate":[170],"applications":[172],"learned":[175],"simulator":[177],"downstream":[179],"tasks":[180],"such":[181],"as":[182],"model-based":[183],"reinforcement":[184],"learning,":[185],"prioritized":[188],"imagination":[189],"improve":[191],"sample":[192],"efficiency,":[193],"demonstrating":[194],"competitive":[195],"performance":[196],"compared":[197],"with":[198],"state-of-the-art":[199],"methods.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}