{"id":"https://openalex.org/W4403791574","doi":"https://doi.org/10.1145/3664647.3681488","title":"WorldGPT: Empowering LLM as Multimodal World Model","display_name":"WorldGPT: Empowering LLM as Multimodal World Model","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791574","doi":"https://doi.org/10.1145/3664647.3681488"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5066775492","display_name":"Zhiqi Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Ge","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-6590-365X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongzhe Huang","orcid":"https://orcid.org/0009-0004-8800-1354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Huang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-8800-1354","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109654793","display_name":"Mingze Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingze Zhou","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3633-0413","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015420479","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0003-2258-1291"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2258-1291","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101477058","display_name":"Guoming Wang","orcid":"https://orcid.org/0000-0003-3131-6916"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoming Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3131-6916","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7356-9711","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9017-2508","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":9.5546,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.98395591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7346","last_page":"7355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9922000169754028,"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/T12031","display_name":"Speech and dialogue systems","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.6313104629516602},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33835548162460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313104629516602},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33835548162460327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W58431123","https://openalex.org/W2296073425","https://openalex.org/W2625366777","https://openalex.org/W2952132648","https://openalex.org/W2984008963","https://openalex.org/W3168154341","https://openalex.org/W3205786327","https://openalex.org/W3216352822","https://openalex.org/W4287125738","https://openalex.org/W4304098310","https://openalex.org/W4312933868","https://openalex.org/W4386066385"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"World":[0],"models":[1,20],"are":[2,21,164,180],"progressively":[3],"being":[4],"employed":[5],"across":[6,64],"diverse":[7],"fields,":[8],"extending":[9],"from":[10],"basic":[11],"environment":[12],"simulation":[13],"to":[14,31,120,154,166],"complex":[15,136],"scenario":[16],"construction.":[17],"However,":[18],"existing":[19],"mainly":[22],"trained":[23],"on":[24,114,182],"domain-specific":[25],"states":[26],"and":[27,29,75,93,131,178],"actions,":[28],"confined":[30],"single-modality":[32],"state":[33,104,123],"representations.":[34],"In":[35],"this":[36],"paper,":[37],"We":[38,138],"introduce":[39],"WorldGPT,":[40],"a":[41,83,102,147],"generalist":[42],"world":[43,57,148],"model":[44,122],"built":[45],"upon":[46],"Multimodal":[47],"Large":[48],"Language":[49],"Model":[50],"(MLLM).":[51],"WorldGPT":[52],"acquires":[53],"an":[54],"understanding":[55,130],"of":[56,62,135],"dynamics":[58,134],"through":[59,157],"analyzing":[60],"millions":[61],"videos":[63],"various":[65],"domains.":[66],"To":[67],"further":[68,139],"enhance":[69],"WorldGPT's":[70,118,141],"capability":[71,119],"in":[72,129,144],"specialized":[73],"scenarios":[74],"long-term":[76],"tasks,":[77],"we":[78,99],"have":[79],"integrated":[80],"it":[81],"with":[82],"novel":[84],"cognitive":[85],"architecture":[86],"that":[87],"combines":[88],"memory":[89],"offloading,":[90],"knowledge":[91],"retrieval,":[92],"context":[94],"reflection.":[95],"As":[96],"for":[97,173],"evaluation,":[98],"build":[100],"WorldNet,":[101],"multimodal":[103,151,160],"transition":[105,124],"prediction":[106],"benchmark":[107],"encompassing":[108],"varied":[109],"real-life":[110],"scenarios.":[111,137],"Conducting":[112],"evaluations":[113],"WorldNet":[115],"directly":[116],"demonstrates":[117],"accurately":[121],"patterns,":[125],"affirming":[126],"its":[127],"effectiveness":[128],"predicting":[132],"the":[133,183],"explore":[140],"emerging":[142],"potential":[143],"serving":[145],"as":[146,168,170],"simulator,":[149],"helping":[150],"agents":[152],"generalize":[153],"unfamiliar":[155],"domains":[156],"efficiently":[158],"synthesising":[159],"instruction":[161],"instances":[162],"which":[163],"proved":[165],"be":[167],"reliable":[169],"authentic":[171],"data":[172],"fine-tuning":[174],"purposes.":[175],"The":[176],"code":[177],"dataset":[179],"available":[181],"https://github.com/DCDmllm/WorldGPT":[184]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}