{"id":"https://openalex.org/W7223367426","doi":"https://doi.org/10.48550/arxiv.2610.30724","title":"Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling","display_name":"Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223367426","doi":"https://doi.org/10.48550/arxiv.2610.30724"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.30724","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30724","pdf_url":"https://arxiv.org/pdf/2610.30724","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/2610.30724","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130362135","display_name":"Yifeng Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Yifeng","raw_affiliation_strings":["ByteDance","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159306320","display_name":"Jinghan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jinghan","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159318674","display_name":"Zhihao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhang, Zhihao","raw_affiliation_strings":["ByteDance","UNC-Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"UNC-Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102971250","display_name":"Yajiao Xiong","orcid":"https://orcid.org/0009-0001-9464-5314","observed_orcids":["https://orcid.org/0009-0001-9464-5314"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong, Yajiao","raw_affiliation_strings":["ByteDance","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159335905","display_name":"Yang Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Yang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159370055","display_name":"Kun Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Kun","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159365507","display_name":"Huishuai Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Huishuai","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159349887","display_name":"Dongyan Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Dongyan","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5619999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5619999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.28540000319480896,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05649999901652336,"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/next-frame-prediction","display_name":"next-frame prediction","score":0.9760000109672546},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/state-predictor","display_name":"state predictor","score":0.5529999732971191},{"id":"https://openalex.org/keywords/action-prediction","display_name":"action prediction","score":0.7329999804496765},{"id":"https://openalex.org/keywords/epic-kitchens-100","display_name":"EPIC-KITCHENS-100","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416999936103821},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306999921798706},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5633000135421753},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.37290000915527344},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.30724","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30724","pdf_url":"https://arxiv.org/pdf/2610.30724","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.2610.30724","doi":"https://doi.org/10.48550/arxiv.2610.30724","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.30724","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:2610.30724","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30724","pdf_url":"https://arxiv.org/pdf/2610.30724","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223367426.pdf","grobid_xml":"https://content.openalex.org/works/W7223367426.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2619947201","https://openalex.org/W4297808394","https://openalex.org/W4310921506","https://openalex.org/W4406755497","https://openalex.org/W4407815020","https://openalex.org/W4417261359","https://openalex.org/W4417531491","https://openalex.org/W6910554155","https://openalex.org/W6947949040","https://openalex.org/W7137837393"],"related_works":["https://openalex.org/W7117304613","https://openalex.org/W4399598058","https://openalex.org/W4417097140","https://openalex.org/W4416959598","https://openalex.org/W4283449034","https://openalex.org/W4417531491","https://openalex.org/W4403920331","https://openalex.org/W2969399927","https://openalex.org/W3099331408","https://openalex.org/W4394861491"],"abstract_inverted_index":{"Video":[0],"provides":[1],"a":[2,12,47,78,97,122,128,145,168],"natural":[3],"source":[4],"of":[5,69,104],"supervision:":[6],"what":[7],"happens":[8],"next":[9,107],"serves":[10],"as":[11],"learning":[13,114],"signal":[14],"for":[15,96,172,242],"visual":[16,80,160,243],"world":[17,244],"modeling.":[18,245],"Yet":[19],"masked":[20],"video":[21],"pretraining":[22,81],"focuses":[23],"on":[24,84,154,203,215],"recovering":[25],"missing":[26],"content":[27,134],"from":[28,36,184],"surrounding":[29],"context":[30],"rather":[31],"than":[32],"predicting":[33],"the":[34,37,65,102,105,112,155,176,188],"future":[35,70],"past.":[38],"Autoregressive":[39],"methods":[40,55],"instead":[41],"predict":[42,180],"forward":[43],"one":[44],"token":[45],"at":[46],"time,":[48],"but":[49],"have":[50],"yet":[51],"to":[52,63,179],"match":[53],"joint-embedding":[54],"in":[56,87,121,226,235],"representation":[57,103],"quality.":[58],"This":[59,116],"gap":[60],"motivates":[61],"us":[62],"revisit":[64],"granularity":[66],"and":[67,135,164,198,207,240],"space":[68,125,237],"prediction.":[71],"In":[72],"this":[73],"work,":[74],"we":[75,166],"introduce":[76],"VANE,":[77],"self-supervised":[79],"framework":[82],"built":[83],"next-frame":[85,233],"prediction":[86,117,234],"embedding":[88,124,236],"space.":[89],"A":[90],"causal":[91],"encoder":[92,178],"summarizes":[93],"past":[94],"observations":[95],"state":[98],"predictor":[99],"that":[100,193,232],"infers":[101],"entire":[106],"frame,":[108],"making":[109],"temporal":[110],"evolution":[111],"primary":[113],"signal.":[115],"is":[118,238],"carried":[119],"out":[120],"fixed":[123],"provided":[126],"by":[127,223],"frozen":[129],"semantic":[130,143],"tokenizer,":[131],"emphasizing":[132],"scene":[133],"structure.":[136],"To":[137,158],"retain":[138],"fine-grained":[139],"spatial":[140],"detail":[141],"alongside":[142],"content,":[144],"lightweight":[146],"auxiliary":[147],"generative":[148],"decoder":[149],"reconstructs":[150],"future-frame":[151],"patches":[152],"conditioned":[153],"predicted":[156],"representations.":[157],"unify":[159],"modeling":[161],"across":[162],"images":[163],"videos,":[165],"construct":[167],"local-to-global":[169],"crop":[170],"sequence":[171],"still":[173],"images,":[174],"allowing":[175],"same":[177,189],"newly":[181],"revealed":[182],"regions":[183],"earlier":[185],"crops":[186],"under":[187],"objective.":[190],"Experiments":[191],"show":[192],"VANE":[194],"improves":[195],"with":[196],"model":[197],"data":[199],"scaling,":[200],"achieving":[201],"SOTA":[202],"most":[204],"anticipation,":[205,218],"recognition,":[206],"dense":[208],"perception":[209],"benchmarks":[210],"among":[211],"unified":[212],"encoders.":[213],"Especially":[214],"EPIC-KITCHENS-100":[216],"action":[217],"it":[219],"surpasses":[220],"V-JEPA":[221],"2.1":[222],"7.1":[224],"points":[225],"mean-class":[227],"recall@5.":[228],"These":[229],"results":[230],"demonstrate":[231],"effective":[239],"scalable":[241]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-24T00:00:00"}