{"id":"https://openalex.org/W7148447167","doi":"https://doi.org/10.48550/arxiv.2604.00813","title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","display_name":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148447167","doi":"https://doi.org/10.48550/arxiv.2604.00813"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.00813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.00813","pdf_url":"https://arxiv.org/pdf/2604.00813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.00813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125988202","display_name":"Sicheng Zuo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuo, Sicheng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111162805","display_name":"Zixun Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Zixun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801903","display_name":"Wenzhao Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Wenzhao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127907773","display_name":"Shaoqing Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Shaoqing","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123452900","display_name":"Fang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Fang","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123465206","display_name":"Hanbing Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Hanbing","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126877340","display_name":"Long Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Long","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011123518","display_name":"Zhi-Xin Yang","orcid":"https://orcid.org/0000-0001-9151-7758","observed_orcids":["https://orcid.org/0000-0001-9151-7758"]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yang, Zhi-Xin","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103740674","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529","observed_orcids":["https://orcid.org/0000-0002-6121-5529"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Jiwen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7544000148773193,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7544000148773193,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.2290000021457672,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.00570000009611249,"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/autonomous-driving","display_name":"autonomous driving","score":0.9819999933242798},{"id":"https://openalex.org/keywords/online-trajectory-planning","display_name":"online trajectory planning","score":0.7120000123977661},{"id":"https://openalex.org/keywords/sliding-window-inference","display_name":"sliding window inference","score":0.6439999938011169},{"id":"https://openalex.org/keywords/feature-caching","display_name":"feature caching","score":0.6169999837875366},{"id":"https://openalex.org/keywords/end-to-end-driving","display_name":"end-to-end driving","score":0.4779999852180481},{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103999853134155},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48980000615119934},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4472000002861023},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.00813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.00813","pdf_url":"https://arxiv.org/pdf/2604.00813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.00813","doi":"https://doi.org/10.48550/arxiv.2604.00813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.00813","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.00813","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.00813","pdf_url":"https://arxiv.org/pdf/2604.00813","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7148447167.pdf","grobid_xml":"https://content.openalex.org/works/W7148447167.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W4226305814","https://openalex.org/W4309795819","https://openalex.org/W4378468525","https://openalex.org/W4387323024","https://openalex.org/W4388926208","https://openalex.org/W4392019867","https://openalex.org/W4399598145","https://openalex.org/W4399759454","https://openalex.org/W4404341829","https://openalex.org/W4404350186","https://openalex.org/W4405254477","https://openalex.org/W4405355507","https://openalex.org/W4405433131","https://openalex.org/W4405434092","https://openalex.org/W4405627552","https://openalex.org/W4413556455","https://openalex.org/W4414984891","https://openalex.org/W4415109354","https://openalex.org/W4415145326","https://openalex.org/W4415193050","https://openalex.org/W4415272869","https://openalex.org/W4415337225","https://openalex.org/W4416063870","https://openalex.org/W4416075228","https://openalex.org/W4416091744","https://openalex.org/W4416255002","https://openalex.org/W4416381351","https://openalex.org/W4416413108","https://openalex.org/W4416450316","https://openalex.org/W4416731372","https://openalex.org/W4417292596","https://openalex.org/W4417357145","https://openalex.org/W4417531488","https://openalex.org/W6891859616","https://openalex.org/W6910554155","https://openalex.org/W6910815265","https://openalex.org/W6929312968","https://openalex.org/W6967128091","https://openalex.org/W7082144516","https://openalex.org/W7101652731","https://openalex.org/W7133338915","https://openalex.org/W7133351785","https://openalex.org/W7137865300","https://openalex.org/W7160124948","https://openalex.org/W7160188953","https://openalex.org/W7160197198"],"related_works":["https://openalex.org/W4417531488","https://openalex.org/W7163644113","https://openalex.org/W7220928206","https://openalex.org/W7164364104","https://openalex.org/W7127914854","https://openalex.org/W7204185710","https://openalex.org/W7108225462","https://openalex.org/W7169844426","https://openalex.org/W7221815409","https://openalex.org/W7204153751"],"abstract_inverted_index":{"End-to-end":[0],"autonomous":[1,50],"driving":[2],"has":[3],"evolved":[4],"from":[5],"the":[6,46,65,123,162],"conventional":[7],"paradigm":[8,39],"based":[9],"on":[10,19,80,171],"sparse":[11],"perception":[12],"into":[13],"vision-language-action":[14],"(VLA)":[15],"models,":[16],"which":[17,107],"focus":[18],"learning":[20],"language":[21],"descriptions":[22],"as":[23,45],"an":[24,35,111],"auxiliary":[25],"task":[26],"to":[27,92,135,157,182],"facilitate":[28],"planning.":[29,94],"In":[30],"this":[31],"paper,":[32],"we":[33,59,98,143],"propose":[34,144],"alternative":[36],"Vision-Geometry-Action":[37],"(VGA)":[38],"that":[40],"advocates":[41],"dense":[42,61,117],"3D":[43,57,62],"geometry":[44,63,74,118,168],"critical":[47],"cue":[48],"for":[49,69,122],"driving.":[51],"As":[52],"vehicles":[53],"operate":[54],"in":[55,110],"a":[56,100,145,154],"world,":[58],"think":[60],"provides":[64],"most":[66,72],"comprehensive":[67],"information":[68],"decision-making.":[70],"However,":[71],"existing":[73],"reconstruction":[75,169],"methods":[76],"(e.g.,":[77],"DVGT)":[78],"rely":[79],"computationally":[81],"expensive":[82],"batch":[83],"processing":[84],"of":[85],"multi-frame":[86],"inputs":[87,109],"and":[88,114,119,131,149,193],"cannot":[89],"be":[90,179],"applied":[91,181],"online":[93,112],"To":[95,139],"address":[96],"this,":[97],"introduce":[99],"streaming":[101,147],"Driving":[102],"Visual":[103],"Geometry":[104],"Transformer":[105],"(DVGT-2),":[106],"processes":[108],"manner":[113],"jointly":[115],"outputs":[116],"trajectory":[120],"planning":[121,183],"current":[124],"frame.":[125],"We":[126],"employ":[127],"temporal":[128],"causal":[129],"attention":[130],"cache":[132],"historical":[133,151],"features":[134],"support":[136],"on-the-fly":[137],"inference.":[138],"further":[140],"enhance":[141],"efficiency,":[142],"sliding-window":[146],"strategy":[148],"use":[150],"caches":[152],"within":[153],"certain":[155],"interval":[156],"avoid":[158],"repetitive":[159],"computations.":[160],"Despite":[161],"faster":[163],"speed,":[164],"DVGT-2":[165,177],"achieves":[166],"superior":[167],"performance":[170],"various":[172],"datasets.":[173],"The":[174],"same":[175],"trained":[176],"can":[178],"directly":[180],"across":[184],"diverse":[185],"camera":[186],"configurations":[187],"without":[188],"fine-tuning,":[189],"including":[190],"closed-loop":[191],"NAVSIM":[192],"open-loop":[194],"nuScenes":[195],"benchmarks.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":14}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-03T00:00:00"}