{"id":"https://openalex.org/W7162685497","doi":"https://doi.org/10.48550/arxiv.2605.27817","title":"Turning Video Models into Generalist Robot Policies","display_name":"Turning Video Models into Generalist Robot Policies","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162685497","doi":"https://doi.org/10.48550/arxiv.2605.27817"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27817","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.2605.27817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104046409","display_name":"Sizhe Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Sizhe Lester","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137240885","display_name":"Evan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Evan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137243483","display_name":"Xingjian Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xingjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137288970","display_name":"Tong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137245242","display_name":"Tao Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037154191","display_name":"Max Simchowitz","orcid":"https://orcid.org/0000-0001-9900-1238"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simchowitz, Max","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016061808","display_name":"Vincent Sitzmann","orcid":"https://orcid.org/0000-0002-0107-5704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sitzmann, Vincent","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/T10653","display_name":"Robot Manipulation and Learning","score":0.2694999873638153,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.2694999873638153,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1574999988079071,"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/T12290","display_name":"Human Motion and Animation","score":0.13760000467300415,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6823999881744385},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6085000038146973},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5670999884605408},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48429998755455017},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.374099999666214},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.35569998621940613},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3416999876499176}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6823999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6639000177383423},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6085000038146973},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3416999876499176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C193081819","wikidata":"https://www.wikidata.org/wiki/Q4132092","display_name":"Video feedback","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27817","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.2605.27817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27817","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"generative":[1],"models":[2,30,41,82],"have":[3],"emerged":[4],"as":[5],"a":[6,105,117,200],"promising":[7],"robotics":[8],"backbone,":[9],"capable":[10],"of":[11,18,52],"generating":[12],"videos":[13],"that":[14,31,109,128,191],"depict":[15],"the":[16,50,57,75,89,92,122,146],"completion":[17],"complex":[19],"tasks":[20],"across":[21,155,178],"embodiments":[22,180],"and":[23,36,91,135,157,165,207],"environments.":[24],"Recent":[25],"work":[26],"proposes":[27],"robot":[28,123,209],"foundation":[29],"jointly":[32],"predict":[33],"future":[34],"observations":[35],"actions":[37],"by":[38,181],"finetuning":[39],"video":[40,58,76,81,113,173,193],"with":[42,98,116,184],"action-labeled":[43],"data.":[44,102],"In":[45],"this":[46],"paper,":[47],"we":[48,144],"test":[49],"limits":[51],"an":[53,63,111],"alternative":[54,202],"approach:":[55],"leave":[56],"planner":[59,77,174],"as-is":[60],"while":[61],"training":[62],"embodiment-specific":[64,186],"inverse":[65],"dynamics":[66],"model":[67,115],"(IDM).":[68],"This":[69],"decoupling":[70],"offers":[71],"several":[72],"natural":[73],"benefits:":[74],"remains":[78],"embodiment-agnostic,":[79],"different":[80,185],"can":[83,94,175],"be":[84,95,176],"interchanged":[85],"easily":[86],"without":[87],"re-training":[88],"IDM,":[90],"IDM":[93,119,130],"independently":[96],"trained":[97],"readily":[99],"available":[100,214],"self-play":[101],"We":[103,126],"present":[104],"closed-loop,":[106],"video-to-action":[107,197],"policy":[108],"combines":[110],"action-free":[112],"world":[114],"carefully-designed":[118],"based":[120],"on":[121,215],"embodiment":[124],"Jacobian.":[125],"demonstrate":[127],"our":[129,216],"design":[131],"is":[132,199],"both":[133],"data-efficient":[134],"scalable":[136],"to":[137],"high-dimensional":[138],"action":[139],"spaces.":[140],"Our":[141,188],"policy,":[142],"which":[143],"coin":[145],"Video-to-Embodied":[147],"Robot":[148],"Action":[149],"Model":[150],"(VERA),":[151],"achieves":[152],"strong":[153],"performance":[154],"simulated":[156],"real-world":[158],"benchmarks,":[159],"including":[160],"zero-shot":[161],"Panda":[162],"arm":[163],"manipulation":[164],"16-DoF":[166],"Allegro-hand":[167],"dexterous":[168],"cube":[169],"re-orientation.":[170],"The":[171],"same":[172],"used":[177],"multiple":[179],"pairing":[182],"it":[183],"IDMs.":[187],"results":[189,212],"show":[190],"decoupled":[192],"planning":[194],"plus":[195],"faithful":[196],"translation":[198],"viable":[201],"route":[203],"towards":[204],"zero-shot,":[205],"cross-embodiment,":[206],"generalizable":[208],"control.":[210],"More":[211],"are":[213],"project":[217],"website:":[218],"https://vera.csail.mit.edu.":[219]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}
