{"id":"https://openalex.org/W7127621662","doi":"https://doi.org/10.48550/arxiv.2602.03747","title":"LIVE: Long-horizon Interactive Video World Modeling","display_name":"LIVE: Long-horizon Interactive Video World Modeling","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127621662","doi":"https://doi.org/10.48550/arxiv.2602.03747"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2602.03747","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03747","pdf_url":"https://arxiv.org/pdf/2602.03747","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.03747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124973788","display_name":"Junchao Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Junchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124983719","display_name":"Ziyang Ye","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Ziyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038941145","display_name":"Xinting Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xinting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125051359","display_name":"Tianyu He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125171445","display_name":"Guiyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083443210","display_name":"Shaoshuai Shi","orcid":"https://orcid.org/0000-0003-2558-181X","observed_orcids":["https://orcid.org/0000-0003-2558-181X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Shaoshuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127948903","display_name":"Jiang Bian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125047830","display_name":"Li Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Li","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9531000256538391,"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":0.9531000256538391,"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":0.021900000050663948,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.008200000040233135,"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/video-world-models","display_name":"video world models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/long-horizon-prediction","display_name":"long-horizon prediction","score":0.8640000224113464},{"id":"https://openalex.org/keywords/error-accumulation","display_name":"error accumulation","score":0.5899999737739563},{"id":"https://openalex.org/keywords/cycle-consistency","display_name":"cycle consistency","score":0.8040000200271606},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.652999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710999846458435},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.03747","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03747","pdf_url":"https://arxiv.org/pdf/2602.03747","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.2602.03747","doi":"https://doi.org/10.48550/arxiv.2602.03747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03747","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.03747","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03747","pdf_url":"https://arxiv.org/pdf/2602.03747","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":[],"sustainable_development_goals_aurora":[{"score":0.7107566595077515,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"video":[1],"world":[2,68],"models":[3,17,38],"predict":[4],"future":[5],"visual":[6],"observations":[7],"conditioned":[8],"on":[9,115,124,153],"actions.":[10],"While":[11],"effective":[12],"over":[13,28],"short":[14],"horizons,":[15],"these":[16],"often":[18],"struggle":[19],"with":[20],"long-horizon":[21,125,154],"generation,":[22],"as":[23],"small":[24],"prediction":[25],"errors":[26],"accumulate":[27],"time.":[29],"Prior":[30],"methods":[31],"alleviate":[32],"this":[33,59],"by":[34],"introducing":[35],"pre-trained":[36],"teacher":[37],"and":[39,48,97,138],"sequence-level":[40],"distribution":[41],"matching,":[42],"which":[43],"incur":[44],"additional":[45],"computational":[46],"cost":[47],"fail":[49],"to":[50,104,143],"prevent":[51],"error":[52,73,126],"propagation":[53],"beyond":[54,161],"the":[55,82,106,116],"training":[56,141,162],"horizon.":[57],"In":[58],"work,":[60],"we":[61,129],"propose":[62],"LIVE,":[63],"a":[64,76,91,100],"Long-horizon":[65],"Interactive":[66],"Video":[67],"modEl":[69],"that":[70,134,148],"enforces":[71],"bounded":[72],"accumulation":[74],"via":[75],"novel":[77],"cycle-consistency":[78],"objective,":[79],"thereby":[80],"eliminating":[81],"need":[83],"for":[84],"teacher-based":[85],"distillation.":[86],"Specifically,":[87],"LIVE":[88,149],"first":[89],"performs":[90],"forward":[92],"rollout":[93,163],"from":[94],"ground-truth":[95],"frames":[96],"then":[98],"applies":[99],"reverse":[101],"generation":[102],"process":[103],"reconstruct":[105],"initial":[107],"state.":[108],"The":[109],"diffusion":[110],"loss":[111],"is":[112],"subsequently":[113],"computed":[114],"reconstructed":[117],"terminal":[118],"state,":[119],"providing":[120],"an":[121,131],"explicit":[122],"constraint":[123],"propagation.":[127],"Moreover,":[128],"provide":[130],"unified":[132],"view":[133],"encompasses":[135],"different":[136],"approaches":[137],"introduce":[139],"progressive":[140],"curriculum":[142],"stabilize":[144],"training.":[145],"Experiments":[146],"demonstrate":[147],"achieves":[150],"state-of-the-art":[151],"performance":[152],"benchmarks,":[155],"generating":[156],"stable,":[157],"high-quality":[158],"videos":[159],"far":[160],"lengths.":[164]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2026-02-06T00:00:00"}