{"id":"https://openalex.org/W7154129659","doi":"https://doi.org/10.48550/arxiv.2604.09059","title":"Learning Vision-Language-Action World Models for Autonomous Driving","display_name":"Learning Vision-Language-Action World Models for Autonomous Driving","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154129659","doi":"https://doi.org/10.48550/arxiv.2604.09059"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09059","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.2604.09059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133532337","display_name":"Guoqing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133498117","display_name":"Pin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Pin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015529526","display_name":"Xiangxuan Ren","orcid":"https://orcid.org/0000-0002-9165-3052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Xiangxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014171593","display_name":"Guodongfang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Guodongfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039248257","display_name":"Bailan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Bailan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133345447","display_name":"CHAO MA","orcid":"https://orcid.org/0009-0004-2456-9098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chao","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":0.9003999829292297,"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":0.9003999829292297,"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":0.030799999833106995,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.012400000356137753,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5727999806404114},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5199000239372253},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43209999799728394},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4115000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5911999940872192},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09059","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.2604.09059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09059","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5361954569816589}],"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":[2,45],"have":[3],"recently":[4],"achieved":[5],"notable":[6],"progress":[7],"in":[8],"end-to-end":[9],"autonomous":[10],"driving":[11,86],"by":[12],"integrating":[13],"perception,":[14],"reasoning,":[15],"and":[16,32,40,106,134,151,162,174,180],"control":[17],"within":[18],"a":[19,70,144,153],"unified":[20],"multimodal":[21],"framework.":[22],"However,":[23],"they":[24,62],"often":[25],"lack":[26],"explicit":[27],"modeling":[28],"of":[29,99],"temporal":[30,107],"dynamics":[31],"global":[33],"world":[34,44,75],"consistency,":[35],"which":[36],"limits":[37],"their":[38],"foresight":[39],"safety.":[41],"In":[42,64],"contrast,":[43],"can":[46],"simulate":[47],"plausible":[48],"future":[49,61,123],"scenes":[50],"but":[51],"generally":[52],"struggle":[53],"to":[54,84,95,126],"reason":[55],"about":[56],"or":[57],"evaluate":[58],"the":[59,97,100,112,128],"imagined":[60,124],"generate.":[63],"this":[65,121,139],"work,":[66],"we":[67,141],"present":[68],"VLA-World,":[69],"simple":[71],"yet":[72],"effective":[73],"VLA":[74,173],"model":[76,117],"that":[77,109,157,168],"unifies":[78],"predictive":[79],"imagination":[80],"with":[81],"reflective":[82],"reasoning":[83,146],"improve":[85],"foresight.":[87],"VLA-World":[88,169],"first":[89],"uses":[90],"an":[91],"action-derived":[92],"feasible":[93],"trajectory":[94],"guide":[96],"generation":[98],"next-frame":[101],"image,":[102],"capturing":[103],"rich":[104],"spatial":[105],"cues":[108],"describe":[110],"how":[111],"surrounding":[113],"environment":[114],"evolves.":[115],"The":[116],"then":[118],"reasons":[119],"over":[120],"self-generated":[122],"frame":[125],"refine":[127],"predicted":[129],"trajectory,":[130],"achieving":[131],"higher":[132],"performance":[133],"better":[135],"interpretability.":[136],"To":[137],"support":[138],"pipeline,":[140],"curate":[142],"nuScenes-GR-20K,":[143],"generative":[145],"dataset":[147],"derived":[148],"from":[149],"nuScenes,":[150],"employ":[152],"three-stage":[154],"training":[155],"strategy":[156],"includes":[158],"pretraining,":[159],"supervised":[160],"fine-tuning,":[161],"reinforcement":[163],"learning.":[164],"Extensive":[165],"experiments":[166],"demonstrate":[167],"consistently":[170],"surpasses":[171],"state-of-the-art":[172],"world-model":[175],"baselines":[176],"on":[177],"both":[178],"planning":[179],"future-generation":[181],"benchmarks.":[182],"Project":[183],"page:":[184],"https://vlaworld.github.io":[185]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}