{"id":"https://openalex.org/W4399758271","doi":"https://doi.org/10.48550/arxiv.2406.09455","title":"Pandora: Towards General World Model with Natural Language Actions and Video States","display_name":"Pandora: Towards General World Model with Natural Language Actions and Video States","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399758271","doi":"https://doi.org/10.48550/arxiv.2406.09455"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.09455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09455","pdf_url":"https://arxiv.org/pdf/2406.09455","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.09455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiang, Jiannan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Jiannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737335","display_name":"Guangyi Liu","orcid":"https://orcid.org/0000-0002-8656-1946","observed_orcids":["https://orcid.org/0000-0002-8656-1946"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guangyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gu, Yi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102148920","display_name":"Qiyue Gao","orcid":"https://orcid.org/0009-0000-3808-3495","observed_orcids":["https://orcid.org/0009-0000-3808-3495"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Qiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125524046","display_name":"Yuting Ning","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning, Yuting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136074160","display_name":"Yuheng Zha","orcid":"https://orcid.org/0009-0001-7341-3434","observed_orcids":["https://orcid.org/0009-0001-7341-3434"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Yuheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101380885","display_name":"Zeyu Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081822522","display_name":"Tianhua Tao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Tianhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049670294","display_name":"Shibo Hao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Shibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081388259","display_name":"Yemin Shi","orcid":"https://orcid.org/0000-0001-9024-7266","observed_orcids":["https://orcid.org/0000-0001-9024-7266"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029648803","display_name":"Zhengzhong Liu","orcid":"https://orcid.org/0009-0007-6686-2577","observed_orcids":["https://orcid.org/0009-0007-6686-2577"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhengzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Eric P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085608858","display_name":"Zhiting Hu","orcid":"https://orcid.org/0000-0002-6239-5031","observed_orcids":["https://orcid.org/0000-0002-6239-5031"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhiting","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":19,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6060000061988831,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6060000061988831,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3910999894142151,"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":0.0007999999797903001,"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/world-models","display_name":"world models","score":0.8479999899864197},{"id":"https://openalex.org/keywords/video-generation","display_name":"video generation","score":0.6010000109672546},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.574999988079071},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.6230000257492065},{"id":"https://openalex.org/keywords/long-horizon-reasoning","display_name":"long-horizon reasoning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/interactive-content-creation","display_name":"interactive content creation","score":0.777999997138977}],"concepts":[{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6313375234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4512263834476471},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3546462953090668},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.16675901412963867},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09962981939315796},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.04623439908027649}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.09455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09455","pdf_url":"https://arxiv.org/pdf/2406.09455","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.09455","doi":"https://doi.org/10.48550/arxiv.2406.09455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09455","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.09455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09455","pdf_url":"https://arxiv.org/pdf/2406.09455","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399758271.pdf","grobid_xml":"https://content.openalex.org/works/W4399758271.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416245331","https://openalex.org/W7114794849","https://openalex.org/W7208729455","https://openalex.org/W4415023877","https://openalex.org/W4391047144","https://openalex.org/W7103191359","https://openalex.org/W7172425541","https://openalex.org/W7164883443","https://openalex.org/W7163197584","https://openalex.org/W7115599092"],"abstract_inverted_index":{"World":[0],"models":[1,28,41,61,163],"simulate":[2],"future":[3],"states":[4,91],"of":[5,35,55,121,158],"the":[6,33,56,67,119],"world":[7,37,68,79,90,162],"in":[8],"response":[9],"to":[10],"different":[11],"actions.":[12,101],"They":[13],"facilitate":[14],"interactive":[15,63],"content":[16],"creation":[17],"and":[18,51,95,108,113,129],"provides":[19],"a":[20,73,77,84,125,130],"foundation":[21,27],"for":[22],"grounded,":[23],"long-horizon":[24],"reasoning.":[25],"Current":[26],"do":[29],"not":[30],"fully":[31],"meet":[32],"capabilities":[34],"general":[36,78,161],"models:":[38],"large":[39],"language":[40,49],"(LLMs)":[42],"are":[43],"constrained":[44],"by":[45,81,92,123,143],"their":[46,52],"reliance":[47],"on":[48],"modality":[50],"limited":[53],"understanding":[54],"physical":[57],"world,":[58],"while":[59],"video":[60,106,132],"lack":[62],"action":[64],"control":[65,98],"over":[66],"simulations.":[69],"This":[70],"paper":[71],"makes":[72],"step":[74],"towards":[75],"building":[76,159],"model":[80,87],"introducing":[82],"Pandora,":[83],"hybrid":[85],"autoregressive-diffusion":[86],"that":[88],"simulates":[89],"generating":[93],"videos":[94],"allows":[96],"real-time":[97],"with":[99,164],"free-text":[100],"Pandora":[102,117,144],"achieves":[103],"domain":[104],"generality,":[105],"consistency,":[107],"controllability":[109],"through":[110],"large-scale":[111],"pretraining":[112],"instruction":[114],"tuning.":[115],"Crucially,":[116],"bypasses":[118],"cost":[120],"training-from-scratch":[122],"integrating":[124],"pretrained":[126,131],"LLM":[127],"(7B)":[128],"model,":[133],"requiring":[134],"only":[135],"additional":[136],"lightweight":[137],"finetuning.":[138],"We":[139],"illustrate":[140],"extensive":[141],"outputs":[142],"across":[145],"diverse":[146],"domains":[147],"(indoor/outdoor,":[148],"natural/urban,":[149],"human/robot,":[150],"2D/3D,":[151],"etc.).":[152],"The":[153],"results":[154],"indicate":[155],"great":[156],"potential":[157],"stronger":[160],"larger-scale":[165],"training.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-06-18T00:00:00"}
