{"id":"https://openalex.org/W7161819207","doi":"https://doi.org/10.48550/arxiv.2605.19950","title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","display_name":"AffectVerse: Emotional World Models for Multimodal Affective Computing","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161819207","doi":"https://doi.org/10.48550/arxiv.2605.19950"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19950","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136514345","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-9525-0541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136603635","display_name":"Fanghua Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Fanghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136586375","display_name":"Yixin Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Yixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136516150","display_name":"Sicheng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Sicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136531447","display_name":"Xiaojiang Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Xiaojiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136548688","display_name":"Zitong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YU, Zitong","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":false,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.8871999979019165,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8871999979019165,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.02160000056028366,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.014800000004470348,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.569100022315979},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4767000079154968},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.438400000333786},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5838000178337097},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5791000127792358},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4767000079154968},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39329999685287476},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19950","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19950","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"infer":[1],"emotions":[2],"by":[3],"integrating":[4],"observed":[5,118],"multimodal":[6,17],"cues":[7,135],"with":[8,45,75],"expectations":[9],"about":[10],"how":[11],"affective":[12,35,58,102,141,179],"states":[13],"may":[14],"unfold.":[15],"Existing":[16],"large":[18],"language":[19],"models":[20],"(MLLMs),":[21],"however,":[22],"often":[23],"treat":[24],"emotion":[25],"recognition":[26],"as":[27,108],"static":[28],"fusion":[29],"over":[30,151],"complete":[31],"audiovisual-text":[32],"inputs,":[33],"leaving":[34],"dynamics":[36],"implicit.":[37],"We":[38],"propose":[39],"AffectVerse,":[40],"a":[41,109,175],"Qwen2.5-Omni-based":[42],"model":[43],"equipped":[44],"an":[46,51],"Emotion":[47],"World":[48],"Module":[49],"(EWM),":[50],"action-free":[52],"representation-level":[53],"module":[54],"for":[55,101,178],"short-horizon":[56],"latent":[57],"prediction.":[59],"\\rev{EWM":[60],"contains":[61],"three":[62],"modules:":[63],"1)":[64],"Cross-Modal":[65],"Temporal":[66],"Imagination":[67],"predicts":[68],"future":[69,106],"video/audio":[70],"representations":[71],"from":[72,160],"past":[73],"tokens":[74,86,97],"multi-step":[76],"rollout.":[77],"2)":[78],"MAMA(Modality-Aware":[79],"Multi-step":[80],"Attention)":[81],"Belief":[82,92],"Aggregation":[83],"compresses":[84],"imagined":[85],"into":[87,98],"modality-aware":[88],"belief":[89,96,130,166],"tokens.":[90],"3)":[91],"Injection":[93],"inserts":[94],"these":[95],"the":[99,128],"LLM":[100],"reasoning.}":[103],"AffectVerse":[104,146],"uses":[105],"prediction":[107],"past-conditioned":[110],"self-supervised":[111],"signal:":[112],"it":[113],"does":[114],"not":[115],"replace":[116],"modeling":[117,173],"history":[119],"or":[120],"require":[121],"unseen":[122],"signals":[123],"at":[124,148],"inference,":[125],"but":[126],"forces":[127],"current":[129],"state":[131],"to":[132],"encode":[133],"transition":[134],"that":[136],"are":[137],"predictive":[138,171],"of":[139],"subsequent":[140],"change.":[142],"Across":[143],"nine":[144],"benchmarks,":[145],"improves":[147],"least":[149],"2.57\\%":[150],"other":[152],"models,":[153],"while":[154],"controlled":[155],"ablations":[156],"show":[157],"additive":[158],"gains":[159],"temporal":[161],"imagination,":[162],"cross-modal":[163],"rollout,":[164],"and":[165],"aggregation.":[167],"These":[168],"results":[169],"suggest":[170],"belief-state":[172],"is":[174],"practical":[176],"alternative":[177],"computing.":[180]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}