{"id":"https://openalex.org/W7164176742","doi":"https://doi.org/10.48550/arxiv.2606.11187","title":"Next Forcing: Causal World Modeling with Multi-Chunk Prediction","display_name":"Next Forcing: Causal World Modeling with Multi-Chunk Prediction","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164176742","doi":"https://doi.org/10.48550/arxiv.2606.11187"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11187","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138327416","display_name":"Gangwei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Gangwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138362128","display_name":"Qihang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138317672","display_name":"Jiaming Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138335348","display_name":"Xing Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138329614","display_name":"Yujun Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138362367","display_name":"Xin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138327623","display_name":"Yinghao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yinghao","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":0.6945000290870667,"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":0.6945000290870667,"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":0.18529999256134033,"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":0.01600000075995922,"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/forcing","display_name":"Forcing (mathematics)","score":0.7775999903678894},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7748000025749207},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5825999975204468},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4674000144004822}],"concepts":[{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7748000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712000012397766},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5210999846458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48669999837875366},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11187","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"doi:10.48550/arxiv.2606.11187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11187","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"video":[1,56,111,228,256,265],"generation":[2],"has":[3],"emerged":[4],"as":[5,31],"a":[6,65,126,190,248],"powerful":[7],"paradigm":[8],"for":[9,70],"World":[10],"Action":[11],"Models":[12],"(WAMs).":[13],"However,":[14],"existing":[15],"approaches":[16],"suffer":[17,49],"from":[18,50,136],"slow":[19,51],"training":[20,33,96,198],"convergence":[21,174],"and":[22,80,156,175,200,204,258],"limited":[23],"converged":[24,177],"accuracy,":[25,79,178],"particularly":[26],"at":[27,113,180,184,196],"high":[28,181],"frame":[29,182],"rates,":[30],"the":[32,38,100,140,164,169,210,218,226,233],"supervision":[34,161],"is":[35],"confined":[36],"to":[37,54,108,145,152,163,224,252],"current":[39,234],"chunk":[40,229],"without":[41],"explicit":[42],"signals":[43],"about":[44],"future":[45,115,147],"dynamics;":[46],"they":[47],"also":[48,242],"inference":[52,238],"due":[53],"iterative":[55],"denoising.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"present":[62],"Next":[63,91,187,240],"Forcing,":[64],"multi-chunk":[66],"prediction":[67,86,130],"(MCP)":[68],"framework":[69],"causal":[71,127],"world":[72],"modeling":[73],"that":[74,98],"enables":[75],"faster":[76,202],"training,":[77,168],"higher":[78],"accelerated":[81],"inference.":[82],"Inspired":[83],"by":[84],"multi-token":[85],"in":[87,230,255],"large":[88],"language":[89],"models,":[90],"Forcing":[92,188,241],"introduces":[93],"an":[94],"MCP":[95,106,123,170,219],"objective":[97],"augments":[99],"main":[101,141,165],"model":[102,142],"with":[103,232],"lightweight":[104],"auxiliary":[105],"modules":[107,124,171,220],"simultaneously":[109],"denoise":[110],"chunks":[112],"multiple":[114,137],"temporal":[116,160],"horizons":[117],"(next$^1$,":[118],"next$^2$,":[119],"next$^3$":[120],"chunks).":[121],"These":[122],"form":[125],"chain":[128],"across":[129],"depths,":[131],"where":[132],"intermediate":[133],"features":[134],"fused":[135],"layers":[138],"of":[139],"are":[143],"leveraged":[144],"predict":[146,225],"dynamics,":[148],"allowing":[149],"near-future":[150],"predictions":[151],"inform":[153],"farther-future":[154],"ones":[155],"providing":[157],"dense":[158],"multi-scale":[159],"back":[162],"model.":[166],"During":[167],"significantly":[172],"accelerate":[173],"improve":[176],"especially":[179],"rates:":[183],"50":[185],"fps,":[186],"achieves":[189],"93.1%":[191],"relative":[192],"improvement":[193],"over":[194,259],"LingBot-VA":[195],"5k":[197],"steps":[199],"2.3x":[201],"convergence,":[203],"establishes":[205],"new":[206],"state-of-the-art":[207],"results":[208],"on":[209,214,246,263],"RoboTwin":[211],"benchmark":[212,249],"(94.1/93.5%":[213],"Clean/Random).":[215],"At":[216],"inference,":[217],"can":[221],"be":[222],"retained":[223],"next":[227],"parallel":[231],"one,":[235],"achieving":[236],"2x":[237],"acceleration.":[239],"demonstrates":[243],"significant":[244],"improvements":[245],"PhyWorld,":[247],"evaluating":[250],"adherence":[251],"physical":[253],"laws":[254],"generation,":[257],"50%":[260],"FVD":[261],"reduction":[262],"general":[264],"pretraining.":[266]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}