{"id":"https://openalex.org/W7151547693","doi":"https://doi.org/10.48550/arxiv.2604.04502","title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","display_name":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7151547693","doi":"https://doi.org/10.48550/arxiv.2604.04502"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04502","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,"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.2604.04502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133077871","display_name":"Zhongru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhongru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133075734","display_name":"Chenghan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chenghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133132602","display_name":"Qingzhou Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Qingzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133082189","display_name":"Yanjiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yanjiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133097008","display_name":"Jianke Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133099471","display_name":"Yucheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133069606","display_name":"Jianyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jianyu","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.46720001101493835,"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":0.46720001101493835,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.2818000018596649,"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":0.08269999921321869,"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/robot","display_name":"Robot","score":0.6854000091552734},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5461999773979187},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4259999990463257},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.40470001101493835},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.37310001254081726},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.37229999899864197},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.3481999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020999789237976},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6854000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406999826431274},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04502","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,"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.2604.04502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04502","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,"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],"generation":[1,27,202],"models":[2,203,208],"have":[3],"advanced":[4,25],"rapidly":[5],"and":[6,117,177],"are":[7],"beginning":[8],"to":[9,130,154,205],"show":[10],"a":[11,40,86,122,165,173,178,191,211],"strong":[12,132],"understanding":[13],"of":[14,135,190],"physical":[15],"dynamics.":[16],"In":[17],"this":[18,111,161],"paper,":[19],"we":[20,163],"investigate":[21],"how":[22],"far":[23],"an":[24,55,98],"video":[26,87,137,201,207],"model":[28,58,88],"such":[29],"as":[30,172,181,200],"Veo-3":[31,45,171],"can":[32,89,100,140,209],"support":[33],"generalizable":[34,215],"robotic":[35],"manipulation.":[36],"We":[37,109,126],"first":[38],"study":[39],"zero-shot":[41],"approach":[42,113],"in":[43,95,114],"which":[44,169],"predicts":[46],"future":[47,93],"image":[48,96],"sequences":[49],"from":[50],"current":[51],"robot":[52,63,107,216],"observations,":[53],"while":[54],"inverse":[56],"dynamics":[57],"IDM":[59,66,99],"recovers":[60],"the":[61,118,131,182,187],"corresponding":[62],"actions.":[64,108],"The":[65,80],"is":[67,83],"trained":[68],"solely":[69],"on":[70],"random-play":[71],"data,":[72],"requiring":[73],"neither":[74],"human":[75],"supervision":[76],"nor":[77],"expert":[78],"demonstrations.":[79],"key":[81],"intuition":[82],"that,":[84,128,199],"if":[85],"generate":[90,142],"physically":[91],"plausible":[92],"motions":[94],"space,":[97],"translate":[101],"those":[102],"visual":[103],"trajectories":[104],"into":[105],"executable":[106],"evaluate":[110],"\"Veo-3+IDM\"":[112],"both":[115],"simulation":[116],"real":[119],"world":[120],"using":[121],"high-dimensional":[123],"dexterous":[124],"hand.":[125],"find":[127],"owing":[129],"generalization":[133],"capability":[134],"frontier":[136],"models,":[138],"Veo-3+IDM":[139],"consistently":[141],"approximately":[143],"correct":[144],"task-level":[145],"trajectories.":[146],"However,":[147],"its":[148],"low-level":[149,183],"control":[150],"accuracy":[151],"remains":[152],"insufficient":[153],"solve":[155],"most":[156],"tasks":[157],"reliably.":[158],"Motivated":[159],"by":[160],"observation,":[162],"develop":[164],"hierarchical":[166],"framework,":[167],"Veo-Act,":[168],"uses":[170],"high-level":[174],"motion":[175],"planner":[176],"VLA":[179],"policy":[180],"executor,":[184],"significantly":[185],"improving":[186],"instruction-following":[188],"performance":[189],"state-of-the-art":[192],"vision-language-action":[193],"policy.":[194],"Overall,":[195],"our":[196],"results":[197],"suggest":[198],"continue":[204],"improve,":[206],"be":[210],"valuable":[212],"component":[213],"for":[214],"learning.":[217]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-08T00:00:00"}