{"id":"https://openalex.org/W7164412707","doi":"https://doi.org/10.48550/arxiv.2606.12403","title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","display_name":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164412707","doi":"https://doi.org/10.48550/arxiv.2606.12403"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12403","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.2606.12403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138434874","display_name":"Zefu Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zefu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113290143","display_name":"Rongxu Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Rongxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138410082","display_name":"Junjia Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Junjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138429703","display_name":"Xiaojuan Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xiaojuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138446669","display_name":"Wenling Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064754069","display_name":"Lue Fan","orcid":"https://orcid.org/0000-0002-2349-0538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Lue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138470352","display_name":"Zhaoxiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhaoxiang","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":0.801800012588501,"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":0.801800012588501,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.053300000727176666,"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":0.04670000076293945,"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/prior-probability","display_name":"Prior probability","score":0.8745999932289124},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6617000102996826},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6075999736785889},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5827999711036682},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8745999932289124},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6617000102996826},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6075999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6064000129699707},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12403","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.2606.12403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12403","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":[{"score":0.7953251600265503,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"inherit":[3],"semantic":[4,111],"grounding":[5],"from":[6,51],"large-scale":[7],"pretraining":[8,35],"and":[9,75,104,113,148,172],"perform":[10],"competently":[11],"across":[12,157],"in-distribution":[13],"manipulation":[14,26,159],"tasks.":[15],"This":[16],"grounding,":[17],"however,":[18],"is":[19,27],"built":[20],"on":[21,71,142,153],"static":[22],"image-text":[23],"pairs,":[24],"whereas":[25],"a":[28,42,52,72,83,105,123,135],"continuous,":[29],"contact-rich":[30],"process":[31],"whose":[32],"dynamics":[33],"this":[34],"cannot":[36],"capture.":[37],"We":[38],"present":[39],"World":[40,132],"Pilot,":[41],"VLA":[43,96],"framework":[44],"that":[45,127],"augments":[46],"the":[47,58,68,87,91,95,102,114,143,149,162],"policy":[48],"with":[49,97,161],"priors":[50,93],"World-Action":[53],"Model":[54],"(WAM),":[55],"routed":[56],"into":[57],"decision":[59],"chain":[60],"through":[61],"two":[62,92],"complementary":[63],"pathways.":[64],"Latent":[65],"Steering":[66,77],"conditions":[67],"perception":[69],"layer":[70],"scene-evolution":[73,115],"latent,":[74],"Action":[76],"supplies":[78],"an":[79,98],"anticipated":[80,99],"trajectory":[81],"as":[82],"motion":[84,107],"prior":[85,116],"to":[86],"action":[88],"generator.":[89],"Together":[90],"equip":[94],"view":[100],"of":[101,140],"scene":[103],"trajectory-level":[106],"hint":[108],"alongside":[109],"its":[110],"conditioning,":[112],"remains":[117],"effective":[118],"even":[119],"when":[120],"supplied":[121],"by":[122],"video-pretrained":[124],"world":[125],"model":[126],"has":[128],"not":[129],"been":[130],"action-post-trained.":[131],"Pilot":[133],"attains":[134],"state-of-the-art":[136],"Total":[137],"success":[138,151],"rate":[139,152],"84.7%":[141],"LIBERO-Plus":[144],"zero-shot":[145],"OOD":[146],"benchmark":[147],"highest":[150],"every":[154],"real-robot":[155],"setting":[156],"four":[158],"tasks,":[160],"largest":[163],"margins":[164],"under":[165],"shifts":[166],"in":[167],"viewpoint,":[168],"geometry,":[169],"deformable":[170],"state,":[171],"pose.":[173],"Project":[174],"Website:":[175],"https://world-pilot.github.io/":[176]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-12T00:00:00"}