{"id":"https://openalex.org/W7128399162","doi":"https://doi.org/10.48550/arxiv.2602.06508","title":"World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy","display_name":"World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy","alternate_titles":[],"publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128399162","doi":"https://doi.org/10.48550/arxiv.2602.06508"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.06508","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06508","pdf_url":"https://arxiv.org/pdf/2602.06508","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"},"parent_works":[],"lineage":["https://openalex.org/W7128399162"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.06508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125427780","display_name":"Xiaokang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaokang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037364812","display_name":"Zechen Bai","orcid":"https://orcid.org/0000-0001-5953-0442","observed_orcids":["https://orcid.org/0000-0001-5953-0442"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Zechen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035310910","display_name":"Hai Ci","orcid":"https://orcid.org/0000-0001-7170-277X","observed_orcids":["https://orcid.org/0000-0001-7170-277X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ci, Hai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101958529","display_name":"Kevin Ma","orcid":"https://orcid.org/0009-0008-8077-4650","observed_orcids":["https://orcid.org/0009-0008-8077-4650","https://orcid.org/0009-0002-5952-1604","https://orcid.org/0009-0009-4231-508X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Kevin Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166","observed_orcids":["https://orcid.org/0000-0002-7681-2166"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shou, Mike Zheng","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":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9785000085830688,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9785000085830688,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.01860000006854534,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010000000474974513,"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/vision-language-action-policies","display_name":"vision-language-action policies","score":0.7519999742507935},{"id":"https://openalex.org/keywords/video-world-models","display_name":"video world models","score":0.9520000219345093},{"id":"https://openalex.org/keywords/closed-loop-learning","display_name":"closed-loop learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.5889999866485596},{"id":"https://openalex.org/keywords/reward-estimation","display_name":"reward estimation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/post-training-fine-tuning","display_name":"post-training fine-tuning","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718999981880188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6973000168800354},{"id":"https://openalex.org/C3019565508","wikidata":"https://www.wikidata.org/wiki/Q444835","display_name":"Virtual world","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.06508","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06508","pdf_url":"https://arxiv.org/pdf/2602.06508","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.2602.06508","doi":"https://doi.org/10.48550/arxiv.2602.06508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06508","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:2602.06508","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06508","pdf_url":"https://arxiv.org/pdf/2602.06508","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128399162.pdf","grobid_xml":"https://content.openalex.org/works/W7128399162.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2745471877","https://openalex.org/W4214570817","https://openalex.org/W4303647933","https://openalex.org/W4323572061","https://openalex.org/W4389115686","https://openalex.org/W4391631327","https://openalex.org/W4392182423","https://openalex.org/W4399695759","https://openalex.org/W4403819024","https://openalex.org/W4403819516","https://openalex.org/W4405903277","https://openalex.org/W4406457559","https://openalex.org/W4409092337","https://openalex.org/W4413146585","https://openalex.org/W4413158071","https://openalex.org/W4414079054","https://openalex.org/W4414581628","https://openalex.org/W4414806737","https://openalex.org/W4415097172","https://openalex.org/W4415337442","https://openalex.org/W4415935378","https://openalex.org/W4416236772","https://openalex.org/W4416780398","https://openalex.org/W4417300442","https://openalex.org/W6910795718","https://openalex.org/W6929480010","https://openalex.org/W6948104436","https://openalex.org/W7081569152","https://openalex.org/W7106821853","https://openalex.org/W7128804563","https://openalex.org/W7129725900","https://openalex.org/W7133220882","https://openalex.org/W7133244780","https://openalex.org/W7160109994","https://openalex.org/W7196929042","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W7163661468","https://openalex.org/W7129725900","https://openalex.org/W7213998990","https://openalex.org/W7221816110","https://openalex.org/W4414806737","https://openalex.org/W7128804563","https://openalex.org/W7223308246","https://openalex.org/W7140205806","https://openalex.org/W4416236772","https://openalex.org/W7219026542"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"can":[3,138],"refine":[4],"Vision-Language-Action":[5],"(VLA)":[6],"policies":[7],"beyond":[8],"behavior":[9,131],"cloning,":[10],"but":[11],"real-world":[12],"RL":[13],"remains":[14],"expensive":[15],"due":[16],"to":[17,32,88,115,167],"extensive":[18],"rollouts,":[19],"resets,":[20],"supervision,":[21],"and":[22,73,85,105,123,169,176],"safety":[23],"risks.":[24],"Action-conditioned":[25],"video":[26,97],"world":[27,98,153,172],"models":[28],"offer":[29],"an":[30],"option":[31],"train":[33,94],"in":[34,124],"virtual":[35],"environments,":[36],"yet":[37],"they":[38,49],"exhibit":[39],"imprecise":[40],"action":[41],"following,":[42],"particularly":[43],"on":[44,59,187],"subtle":[45],"near-success":[46,86],"failures.":[47],"Besides,":[48],"lack":[50],"native":[51],"reward":[52,113],"signals":[53],"for":[54,155],"RL.":[55],"Computing":[56],"rewards":[57,107],"based":[58],"inaccurate":[60],"visual":[61,127],"predictions":[62],"remain":[63],"unreliable.":[64],"We":[65,78],"introduce":[66],"World-VLA-Loop,":[67],"structured":[68],"around":[69],"two":[70],"foundational":[71],"designs":[72],"a":[74,95,120,135],"higher-level":[75],"co-evolving":[76],"paradigm.":[77],"first":[79],"curate":[80],"SANS,":[81],"dedicatedly":[82],"mixing":[83],"successful":[84],"trajectories":[87],"improve":[89],"action-outcome":[90],"alignment.":[91],"Then,":[92],"we":[93],"state-aware":[96],"model":[99,154],"that":[100],"jointly":[101],"predicts":[102],"future":[103],"frames":[104],"binary":[106],"from":[108,162],"diffusion":[109],"latents.":[110],"It":[111],"couples":[112],"estimation":[114],"the":[116,141,147,151,171],"generator":[117],"rather":[118],"than":[119],"separate":[121],"module,":[122],"turn,":[125],"benefits":[126],"prediction.":[128],"Since":[129],"VLA":[130,157,182],"shifts":[132],"during":[133],"RL,":[134],"fixed":[136],"simulator":[137],"misalign":[139],"with":[140],"updated":[142],"policy,":[143],"World-VLA-Loop":[144,179],"therefore":[145],"closes":[146],"loop":[148],"by":[149],"using":[150],"refined":[152],"iterative":[156],"post-training":[158],"while":[159,184],"feeding":[160],"rollouts":[161],"each":[163],"improved":[164],"policy":[165],"back":[166],"augment":[168],"fine-tune":[170],"model.":[173],"Across":[174],"simulation":[175],"real-robot":[177],"experiments,":[178],"substantially":[180],"improves":[181],"performance":[183],"reducing":[185],"reliance":[186],"costly":[188],"physical":[189],"interaction.":[190]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7128399162","counts_by_year":[{"year":2026,"cited_by_count":52},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-02-10T00:00:00"}
