{"id":"https://openalex.org/W4417460464","doi":"https://doi.org/10.48550/arxiv.2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","display_name":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417460464","doi":"https://doi.org/10.48550/arxiv.2512.13604"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2512.13604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13604","pdf_url":"https://arxiv.org/pdf/2512.13604","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.13604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gao, Jianxiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jianxiong","raw_affiliation_strings":["Time World"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Time World","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Zhaoxi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen, Zhaoxi","raw_affiliation_strings":["NTU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349363","display_name":"Xian Liu","orcid":"https://orcid.org/0000-0002-1662-477X","observed_orcids":["https://orcid.org/0000-0002-1662-477X"]},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Liu, Xian","raw_affiliation_strings":["NVIDIA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA ,","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110808792","display_name":"Junhao Zhuang","orcid":"https://orcid.org/0000-0002-1642-0750","observed_orcids":["https://orcid.org/0000-0002-1642-0750"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang, Junhao","raw_affiliation_strings":["THU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"THU ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Chengming","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chengming","raw_affiliation_strings":["Time World"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Time World","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080019095","display_name":"Jianfeng Feng","orcid":"https://orcid.org/0000-0002-9328-5732","observed_orcids":["https://orcid.org/0000-0002-9328-5732"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Jianfeng","raw_affiliation_strings":["Time World"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Time World","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiao, Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":["Shanghai AI Laboratory https :// vchitect.github.io /LongVie2- project /"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory https :// vchitect.github.io /LongVie2- project /","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fu, Yanwei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yanwei","raw_affiliation_strings":["Time World"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Time World","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121688503","display_name":"Chenyang Si","orcid":"https://orcid.org/0000-0002-3354-1968","observed_orcids":["https://orcid.org/0000-0002-3354-1968"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115589625","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0001-6176-5451","observed_orcids":["https://orcid.org/0000-0001-6176-5451","https://orcid.org/0009-0005-9503-0548"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liu, Ziwei","raw_affiliation_strings":["NTU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU ,","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.0,"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/video-world-models","display_name":"video world models","score":0.7820000052452087},{"id":"https://openalex.org/keywords/controllable-video-generation","display_name":"controllable video generation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/multimodal-guidance","display_name":"multimodal guidance","score":0.8059999942779541},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.9319999814033508},{"id":"https://openalex.org/keywords/autoregressive-video-generation","display_name":"autoregressive video generation","score":0.828000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046000003814697},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.13604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13604","pdf_url":"https://arxiv.org/pdf/2512.13604","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.13604","doi":"https://doi.org/10.48550/arxiv.2512.13604","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13604","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.13604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13604","pdf_url":"https://arxiv.org/pdf/2512.13604","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":null,"license_id":null,"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/W4417460464.pdf","grobid_xml":"https://content.openalex.org/works/W4417460464.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W4402387301","https://openalex.org/W4405956131","https://openalex.org/W4406458128","https://openalex.org/W4407794264","https://openalex.org/W4409092337","https://openalex.org/W4412587524","https://openalex.org/W4413155399","https://openalex.org/W4414452104","https://openalex.org/W4414699649","https://openalex.org/W4414886176","https://openalex.org/W4414928226","https://openalex.org/W4415089914","https://openalex.org/W4415270647","https://openalex.org/W4416047763","https://openalex.org/W4417036201","https://openalex.org/W4417086758","https://openalex.org/W4417087231","https://openalex.org/W4417126972","https://openalex.org/W4417136857","https://openalex.org/W6947980884","https://openalex.org/W7081565860","https://openalex.org/W7083825679","https://openalex.org/W7106797690","https://openalex.org/W7109087662"],"related_works":["https://openalex.org/W4417163885","https://openalex.org/W4416047763","https://openalex.org/W4405355504","https://openalex.org/W7131879756","https://openalex.org/W7166558390","https://openalex.org/W4416138746","https://openalex.org/W4416949833","https://openalex.org/W7118449068","https://openalex.org/W4414897100","https://openalex.org/W7163079094"],"abstract_inverted_index":{"Building":[0],"video":[1,6,154,167],"world":[2,20,168],"models":[3],"upon":[4],"pretrained":[5],"generation":[7,155],"systems":[8],"represents":[9],"an":[10,55],"important":[11],"yet":[12],"challenging":[13],"step":[14,164],"toward":[15,47,165],"general":[16],"spatiotemporal":[17],"intelligence.":[18],"A":[19],"model":[21],"should":[22],"possess":[23],"three":[24,61],"essential":[25],"properties:":[26],"controllability,":[27,145],"long-term":[28,94],"visual":[29,99,149],"quality,":[30],"and":[31,44,69,78,93,101,131,148,151],"temporal":[32,114,146],"consistency.":[33,115],"To":[34],"this":[35],"end,":[36],"we":[37],"take":[38],"a":[39,120,162],"progressive":[40],"approach-first":[41],"enhancing":[42],"controllability":[43],"then":[45],"extending":[46],"long-term,":[48],"high-quality":[49],"generation.":[50],"We":[51,116],"present":[52],"LongVie":[53,138],"2,":[54],"end-to-end":[56],"autoregressive":[57],"framework":[58],"trained":[59],"in":[60,143],"stages:":[62],"(1)":[63],"Multi-modal":[64],"guidance,":[65,104],"which":[66,105],"integrates":[67],"dense":[68],"sparse":[70],"control":[71],"signals":[72],"to":[73,96,112,158],"provide":[74],"implicit":[75],"world-level":[76],"supervision":[77],"improve":[79],"controllability;":[80],"(2)":[81],"Degradation-aware":[82],"training":[83,92],"on":[84],"the":[85,89],"input":[86],"frame,":[87],"bridging":[88],"gap":[90],"between":[91],"inference":[95],"maintain":[97],"high":[98],"quality;":[100],"(3)":[102],"History-context":[103],"aligns":[106],"contextual":[107],"information":[108],"across":[109],"adjacent":[110],"clips":[111],"ensure":[113],"further":[117],"introduce":[118],"LongVGenBench,":[119],"comprehensive":[121],"benchmark":[122],"comprising":[123],"100":[124],"high-resolution":[125],"one-minute":[126],"videos":[127],"covering":[128],"diverse":[129],"real-world":[130],"synthetic":[132],"environments.":[133],"Extensive":[134],"experiments":[135],"demonstrate":[136],"that":[137],"2":[139],"achieves":[140],"state-of-the-art":[141],"performance":[142],"long-range":[144],"coherence,":[147],"fidelity,":[150],"supports":[152],"continuous":[153],"lasting":[156],"up":[157],"five":[159],"minutes,":[160],"marking":[161],"significant":[163],"unified":[166],"modeling.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-17T00:00:00"}