{"id":"https://openalex.org/W7138241013","doi":"https://doi.org/10.1609/aaai.v40i3.37162","title":"Reality vs Counterfactual: Multi-World Contrastive Reinforcement Learning for Enhancing MLLM\u2019s Theory of Mind in Egocentric Videos","display_name":"Reality vs Counterfactual: Multi-World Contrastive Reinforcement Learning for Enhancing MLLM\u2019s Theory of Mind in Egocentric Videos","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138241013","doi":"https://doi.org/10.1609/aaai.v40i3.37162"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i3.37162","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37162","pdf_url":null,"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://doi.org/10.1609/aaai.v40i3.37162","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101963058","display_name":"Guiyang Hou","orcid":"https://orcid.org/0009-0009-9163-0633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guiyang Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730292","display_name":"Yihui Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672370","display_name":"Chen Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743842","display_name":"Xiang  Long Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695961","display_name":"Zhe Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664295","display_name":"Wenqi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668340","display_name":"Yongliang Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongliang Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129703302","display_name":"Weiming Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiming Lu","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":"40","issue":"3","first_page":"1828","last_page":"1836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3977000117301941,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3977000117301941,"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":0.12139999866485596,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0560000017285347,"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/embodied-cognition","display_name":"Embodied cognition","score":0.7520999908447266},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6723999977111816},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5659999847412109},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"Theory of mind","score":0.412200003862381},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.36730000376701355},{"id":"https://openalex.org/keywords/mental-model","display_name":"Mental model","score":0.33399999141693115},{"id":"https://openalex.org/keywords/mental-image","display_name":"Mental image","score":0.3278000056743622}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7520999908447266},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5489000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216000080108643},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.46070000529289246},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38580000400543213},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C4051589","wikidata":"https://www.wikidata.org/wiki/Q860959","display_name":"Mental image","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i3.37162","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37162","pdf_url":null,"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:ojs.aaai.org:article/37162","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37162","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37162","pdf_url":null,"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4567226767539978}],"awards":[{"id":"https://openalex.org/G7036249533","display_name":null,"funder_award_id":"62376245","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/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Theory":[0],"of":[1,115,140],"Mind":[2],"(ToM)":[3],"refers":[4],"to":[5,8,22,35,80,91,122],"the":[6,123,138,151,155],"ability":[7,34],"infer":[9,92],"others'":[10],"mental":[11,39,94],"states,":[12],"which":[13],"is":[14],"an":[15,60],"essential":[16],"capability":[17],"for":[18],"embodied":[19,61],"AI":[20],"agents":[21],"effectively":[23],"collaborate":[24],"and":[25,83,98,106,118,126,146,148,161],"interact":[26],"with":[27],"humans.":[28],"While":[29],"improving":[30],"Large":[31,50],"Language":[32,51],"Models'":[33,52],"reason":[36],"about":[37],"characters'":[38],"states":[40,95],"in":[41,56,87],"text-based":[42],"stories/dialogues":[43],"has":[44],"been":[45],"extensively":[46],"studied,":[47],"enhancing":[48],"Multimodal":[49],"ToM":[53],"capabilities,":[54],"particularly":[55],"egocentric":[57],"video":[58],"from":[59],"perspective,":[62],"remains":[63],"unexplored.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,136],"propose":[69],"a":[70],"contrastive":[71],"Reinforcement":[72],"Learning":[73],"(RL)":[74],"paradigm":[75],"that":[76,109],"explicitly":[77],"encourages":[78],"models":[79],"leverage":[81],"temporal":[82],"causal":[84],"evolutionary":[85],"patterns":[86],"user":[88],"action":[89],"sequences":[90],"user's":[93],"(goals,":[96],"beliefs,":[97],"potential":[99],"next":[100],"actions).":[101],"Evaluation":[102],"results":[103],"on":[104],"in-domain":[105],"out-of-domain":[107],"demonstrate":[108],"our":[110,162],"method":[111],"achieves":[112],"performance":[113,139],"improvements":[114],"(+30.00%,":[116],"+2.00%)":[117],"(+5.83%,":[119],"+5.00%)":[120],"compared":[121],"backbone":[124],"model":[125],"vanilla":[127,158],"Group":[128],"Relative":[129],"Policy":[130],"Optimization":[131],"(GRPO)":[132],"model,":[133,157,160],"respectively.":[134],"Additionally,":[135],"compare":[137],"two":[141],"post-training":[142],"paradigms":[143],"(Supervise":[144],"Fine-Tuning":[145],"RL)":[147],"systematically":[149],"analyze":[150],"reasoning":[152],"trajectories":[153],"across":[154],"base":[156],"GRPO":[159],"proposed":[163],"method.":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}