{"id":"https://openalex.org/W7160947000","doi":"https://doi.org/10.48550/arxiv.2605.10426","title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","display_name":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160947000","doi":"https://doi.org/10.48550/arxiv.2605.10426"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10426","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.2605.10426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052445703","display_name":"Minqing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Minqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135910463","display_name":"Yujiao Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Yujiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135950042","display_name":"Zihan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135955179","display_name":"Jiajie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiajie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136001440","display_name":"Jingqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135918869","display_name":"Zhi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135917722","display_name":"Feiyang Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Feiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009482239","display_name":"Hangning Zhou","orcid":"https://orcid.org/0009-0009-8894-3137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hangning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135974681","display_name":"Mu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135954510","display_name":"Gong Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che, Gong","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":0.4772999882698059,"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":0.4772999882698059,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.3944000005722046,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.024800000712275505,"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/action","display_name":"Action (physics)","score":0.5608000159263611},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4397999942302704},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4390999972820282},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41679999232292175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6644999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931000113487244},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2906999886035919}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10426","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.2605.10426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10426","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":[{"score":0.44173139333724976,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"emerged":[4],"as":[5,41,66,192],"a":[6,42,54,130],"promising":[7],"paradigm":[8],"for":[9,45,59,195],"end-to-end":[10],"autonomous":[11,60],"driving.":[12],"However,":[13],"existing":[14],"reasoning":[15,36,57],"mechanisms":[16],"still":[17],"struggle":[18],"to":[19,28,39,69,147],"provide":[20],"planning-oriented":[21],"intermediate":[22],"representations:":[23],"textual":[24],"Chain-of-Thought":[25],"(CoT)":[26],"fails":[27],"preserve":[29],"continuous":[30,149],"spatiotemporal":[31],"structure,":[32,105,118],"while":[33],"latent":[34],"world":[35,56,63,76],"remains":[37],"difficult":[38],"use":[40],"direct":[43],"condition":[44],"action":[46,71,126,196],"generation.":[47,197],"In":[48],"this":[49],"paper,":[50],"we":[51,96],"propose":[52],"CoWorld-VLA,":[53],"multi-expert":[55,133],"framework":[58],"driving,":[61],"where":[62],"representations":[64],"serve":[65],"explicit":[67],"conditions":[68,194],"guide":[70],"planning.":[72],"CoWorld-VLA":[73,128,155],"extracts":[74],"complementary":[75],"information":[77],"through":[78],"multi-source":[79],"supervision":[80],"and":[81,108,122,164,177,189],"encodes":[82],"it":[83],"into":[84],"expert":[85,187],"tokens":[86,188],"within":[87],"the":[88,143,167,184],"VLA,":[89],"thereby":[90],"providing":[91],"planner-accessible":[92],"conditioning":[93],"signals.":[94],"Specifically,":[95],"construct":[97],"four":[98],"types":[99],"of":[100,186],"tokens:":[101],"semantic":[102],"interaction,":[103],"geometric":[104],"dynamic":[106],"evolution,":[107],"ego":[109,150],"trajectory":[110,178],"tokens,":[111],"which":[112,136],"respectively":[113],"model":[114],"interaction":[115],"intent,":[116],"spatial":[117],"future":[119,161],"temporal":[120],"dynamics,":[121],"behavioral":[123],"goals.":[124],"During":[125],"generation,":[127],"employs":[129],"diffusion-based":[131],"hierarchical":[132],"fusion":[134],"planner,":[135],"is":[137],"coupled":[138],"with":[139],"scene":[140,162],"context":[141],"throughout":[142],"joint":[144],"denoising":[145],"process":[146],"generate":[148],"trajectories.":[151],"Experiments":[152],"show":[153],"that":[154],"achieves":[156],"competitive":[157],"results":[158],"in":[159,174],"both":[160],"generation":[163],"planning":[165,193],"on":[166],"NAVSIM":[168],"v1":[169],"benchmark,":[170],"demonstrating":[171],"strong":[172],"performance":[173],"collision":[175],"avoidance":[176],"accuracy.":[179],"Ablation":[180],"studies":[181],"further":[182],"validate":[183],"complementarity":[185],"their":[190],"effectiveness":[191],"Code":[198],"will":[199],"be":[200],"available":[201],"at":[202],"https://github.com/AFARI-Research/CoWorld-VLA.":[203]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}