{"id":"https://openalex.org/W7125936778","doi":"https://doi.org/10.1109/smc58881.2025.11343429","title":"Cross-Modal World Models for Offline Visual Reinforcement Learning","display_name":"Cross-Modal World Models for Offline Visual Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125936778","doi":"https://doi.org/10.1109/smc58881.2025.11343429"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124131544","display_name":"Qi 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":"Qi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101896775","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-7394-0210"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013457955","display_name":"Baao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baao Xie","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]},{"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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124096975","display_name":"Wenjun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China","institution_ids":["https://openalex.org/I4210165339"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65597284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1570","last_page":"1575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4580000042915344,"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":0.4580000042915344,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10769999772310257,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07909999787807465,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8752999901771545},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8453999757766724},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5187000036239624},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3991999924182892},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.392300009727478}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8752999901771545},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8453999757766724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6976000070571899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5806999802589417},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4490000009536743},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40310001373291016},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.43551555275917053}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2164943005","https://openalex.org/W3168236455","https://openalex.org/W4252279978","https://openalex.org/W4312643908","https://openalex.org/W4383112908","https://openalex.org/W4402029513","https://openalex.org/W4409147637","https://openalex.org/W4409347538"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,14,60,167],"(RL)":[3],"with":[4,54,118],"visual":[5,63],"pixels":[6],"encounters":[7],"two":[8,83],"primary":[9],"challenges:":[10],"overfitting":[11,126],"in":[12,103,127],"representation":[13,129],"induced":[15,183],"by":[16,184],"limited":[17],"data,":[18],"and":[19,42,93],"value":[20,154,181],"overestimation":[21,182],"of":[22,52,61,105,140,155,169,189,199],"out-of-distribution":[23,185],"states.":[24,186],"Recent":[25],"work":[26],"has":[27],"adopted":[28],"accessible":[29,55],"simulators":[30,57],"to":[31,124,136,164],"mitigate":[32],"these":[33,67],"issues,":[34],"but":[35],"rendering":[36],"images":[37],"introduces":[38],"additional":[39],"computational":[40],"costs":[41],"training":[43,151],"challenges.":[44],"In":[45,144],"this":[46,145],"paper,":[47],"we":[48,69,81,113],"study":[49],"the":[50,106,111,115,138,148,153,156,166,170,197],"problem":[51],"anti-exploration":[53,162],"state-based":[56],"for":[58],"effective":[59],"offline":[62,128,171],"control.":[64],"To":[65],"address":[66],"challenges,":[68],"introduce":[70],"a":[71,86,94],"model-based":[72],"RL":[73,172],"framework,":[74],"dubbed":[75],"Cross-Modal":[76],"World":[77],"Models":[78],"(X-MWM).":[79],"Concretely,":[80],"build":[82],"independent":[84],"agents:":[85],"source":[87,116,157],"model":[88,96],"trained":[89],"on":[90,194],"low-dimensional":[91],"states":[92],"target":[95,149,168],"that":[97],"learns":[98],"from":[99],"high-dimensional":[100],"images.":[101],"Initially,":[102],"light":[104],"reward":[107],"function":[108],"discrepancy":[109],"between":[110],"domains,":[112],"pretrain":[114],"agent":[117,150],"latent":[119,132,141],"disagreement-based":[120],"intrinsic":[121],"rewards.":[122],"Subsequently,":[123],"prevent":[125],"learning,":[130],"cross-modal":[131],"alignment":[133],"is":[134],"employed":[135],"close":[137],"distance":[139],"state":[142],"distributions.":[143],"way,":[146],"during":[147],"phase,":[152],"critic":[158],"serves":[159],"as":[160],"an":[161],"constraint":[163],"adjust":[165],"agent,":[173],"which":[174],"encourages":[175],"more":[176],"conservative":[177],"behavior,":[178],"effectively":[179],"alleviating":[180],"Experimental":[187],"results":[188],"various":[190],"robotic":[191],"manipulation":[192],"tasks":[193],"MetaWorld":[195],"validate":[196],"superiority":[198],"our":[200],"approach.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}