{"id":"https://openalex.org/W4414579621","doi":"https://doi.org/10.1109/iccv51701.2025.00250","title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","display_name":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414579621","doi":"https://doi.org/10.1109/iccv51701.2025.00250"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.08751","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341321","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-7028-4956"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957143","display_name":"Zhipeng Zhang","orcid":"https://orcid.org/0000-0002-3733-697X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013457955","display_name":"Baao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baao Xie","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023967844","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-6655-3888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695378","display_name":"Yunbo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Wang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437632","display_name":"Shiyu Wang","orcid":"https://orcid.org/0000-0002-8201-8022"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Wang","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110932383","display_name":"Liaomo Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liaomo Zheng","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120842"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaokang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101739843","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22309062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2599","last_page":"2608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8754000067710876,"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":0.8754000067710876,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7828999757766724,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7653999924659729,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7023000121116638},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5519999861717224},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4262000024318695},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39989998936653137},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3968000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241999745368958},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7023000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136999726295471},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45190000534057617},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.08751","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08751","pdf_url":"https://arxiv.org/pdf/2503.08751","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08751","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08751","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.08751","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08751","pdf_url":"https://arxiv.org/pdf/2503.08751","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1445079709","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2331728944","display_name":null,"funder_award_id":"62250062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3527258163","display_name":null,"funder_award_id":"62302246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G365345849","display_name":null,"funder_award_id":"2024ZD0801200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G371774901","display_name":null,"funder_award_id":"62302246,62250062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6261746788","display_name":null,"funder_award_id":"LQ23F010008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"visual":[1],"reinforcement":[2],"learning":[3,41],"(RL)":[4],"in":[5,20,52,130,172],"practical":[6],"scenarios":[7],"presents":[8],"a":[9,144],"significant":[10],"challenge,":[11],"$\\textit{i.e.,}$":[12],"RL":[13,85],"agents":[14],"suffer":[15],"from":[16,42,62,108,138,161],"low":[17],"sample":[18],"efficiency":[19],"environments":[21],"with":[22,101],"variations.":[23],"While":[24],"various":[25,188],"approaches":[26],"have":[27],"attempted":[28],"to":[29,55,104,121,147],"alleviate":[30],"this":[31],"issue":[32],"by":[33],"disentangled":[34,176],"representation":[35,177],"learning,":[36],"these":[37],"methods":[38],"usually":[39],"start":[40],"scratch":[43],"without":[44],"prior":[45],"knowledge":[46,78,107,137],"of":[47,114,157,168,184],"the":[48,95,115,122,131,136,139,148,152,155,166,169,175,182],"world.":[49],"This":[50],"paper,":[51],"contrast,":[53],"tries":[54],"learn":[56],"and":[57,69,142,159],"understand":[58],"underlying":[59],"semantic":[60,77,106],"variations":[61],"distracting":[63,109],"videos":[64],"via":[65],"offline-to-online":[66],"latent":[67,126],"distillation":[68],"flexible":[70],"disentanglement":[71,102,112,145],"constraints.":[72],"To":[73],"enable":[74],"effective":[75],"cross-domain":[76],"transfer,":[79],"we":[80,93,134],"introduce":[81,143],"an":[82],"interpretable":[83],"model-based":[84],"framework,":[86],"dubbed":[87],"Disentangled":[88],"World":[89],"Models":[90],"(DisWM).":[91],"Specifically,":[92],"pretrain":[94],"action-free":[96],"video":[97],"prediction":[98],"model":[99,117,124,141],"offline":[100],"regularization":[103],"extract":[105],"videos.":[110],"The":[111],"capability":[113],"pretrained":[116,140],"is":[118],"then":[119],"transferred":[120],"world":[123,149],"through":[125],"distillation.":[127],"For":[128],"finetuning":[129],"online":[132,162],"environment,":[133],"exploit":[135],"constraint":[146],"model.":[150],"During":[151],"adaptation":[153],"phase,":[154],"incorporation":[156],"actions":[158],"rewards":[160],"environment":[163],"interactions":[164],"enriches":[165],"diversity":[167],"data,":[170],"which":[171],"turn":[173],"strengthens":[174],"learning.":[178],"Experimental":[179],"results":[180],"validate":[181],"superiority":[183],"our":[185],"approach":[186],"on":[187],"benchmarks.":[189]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}