{"id":"https://openalex.org/W7214745133","doi":"https://doi.org/10.48550/arxiv.2609.34085","title":"AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving","display_name":"AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214745133","doi":"https://doi.org/10.48550/arxiv.2609.34085"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34085","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34085","pdf_url":"https://arxiv.org/pdf/2609.34085","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/2609.34085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153482000","display_name":"Haoran Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Haoran","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118983622","display_name":"Wancong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Wancong","raw_affiliation_strings":["AMI Labs {hz1922 , wz1232 ,","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMI Labs {hz1922 , wz1232 ,","institution_ids":[]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":"https://orcid.org/0000-0002-1992-2684","observed_orcids":["https://orcid.org/0000-0002-1992-2684"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LeCun, Yann","raw_affiliation_strings":["AMI Labs {hz1922 , wz1232 ,","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMI Labs {hz1922 , wz1232 ,","institution_ids":[]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006452373","display_name":"Anna Choromanska","orcid":"https://orcid.org/0000-0002-2556-7009","observed_orcids":["https://orcid.org/0000-0002-2556-7009"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choromanska, Anna","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5234000086784363,"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":0.5234000086784363,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.45210000872612,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.007300000172108412,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7829999923706055},{"id":"https://openalex.org/keywords/end-to-end-autonomous-driving","display_name":"end-to-end autonomous driving","score":0.824999988079071},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.7200000286102295},{"id":"https://openalex.org/keywords/jepa","display_name":"JEPA","score":0.9150000214576721},{"id":"https://openalex.org/keywords/inference-acceleration","display_name":"inference acceleration","score":0.6629999876022339},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.734000027179718},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/trajectory-planning","display_name":"trajectory planning","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642999887466431},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085999965667725},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C2776865275","wikidata":"https://www.wikidata.org/wiki/Q311666","display_name":"Projector","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34085","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34085","pdf_url":"https://arxiv.org/pdf/2609.34085","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.2609.34085","doi":"https://doi.org/10.48550/arxiv.2609.34085","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34085","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:2609.34085","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34085","pdf_url":"https://arxiv.org/pdf/2609.34085","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214745133.pdf","grobid_xml":"https://content.openalex.org/works/W7214745133.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2342840547","https://openalex.org/W2795843265","https://openalex.org/W4286695273","https://openalex.org/W4366208220","https://openalex.org/W4387294122","https://openalex.org/W4389157290","https://openalex.org/W4392019867","https://openalex.org/W4394861491","https://openalex.org/W4399598145","https://openalex.org/W4399657820","https://openalex.org/W4403809229","https://openalex.org/W4404355547","https://openalex.org/W4404360744","https://openalex.org/W4407719570","https://openalex.org/W4416075228","https://openalex.org/W4416338927","https://openalex.org/W4417261359","https://openalex.org/W6910554155","https://openalex.org/W6929312968","https://openalex.org/W7118009763","https://openalex.org/W7126273793","https://openalex.org/W7127358364","https://openalex.org/W7129057078","https://openalex.org/W7135188753","https://openalex.org/W7140141371","https://openalex.org/W7140875411","https://openalex.org/W7150938507","https://openalex.org/W7163152452","https://openalex.org/W7166853236","https://openalex.org/W7171393015","https://openalex.org/W7172308214","https://openalex.org/W7203937597","https://openalex.org/W7204096338","https://openalex.org/W7204197618","https://openalex.org/W7204560724"],"related_works":["https://openalex.org/W7204096338","https://openalex.org/W7203714708","https://openalex.org/W4416887510","https://openalex.org/W7118497878","https://openalex.org/W7140875411","https://openalex.org/W7202118011","https://openalex.org/W7172308214","https://openalex.org/W7151563113","https://openalex.org/W7203937597","https://openalex.org/W7129057078"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,40,69,82,151],"requires":[2],"\\textit{world":[3],"models}":[4],"that":[5,56,73,207],"can":[6],"understand":[7],"the":[8,114,122,153,158,167,184,208],"physical":[9],"world,":[10],"reason":[11],"and":[12,14,35,121,195],"plan,":[13],"operate":[15],"safely.":[16],"In":[17],"this":[18,95],"paper,":[19],"we":[20,49,97],"first":[21],"systematically":[22],"evaluate":[23],"existing":[24,74],"action-conditioned":[25],"joint-embedding":[26],"predictive":[27],"architecture":[28],"(JEPA)":[29],"world":[30,76,154],"models,":[31],"including":[32],"LeWM,":[33],"DINO-WM,":[34],"JEPA-WM":[36],"for":[37,81,91,140],"end-to-end":[38],"autonomous":[39],"(E2EAD).":[41],"To":[42,93],"isolate":[43],"world-model":[44,174],"quality":[45],"from":[46,217],"policy":[47],"learning,":[48],"employ":[50],"a":[51,102,128,137],"goal-conditioned":[52,201],"zero-shot":[53,202],"planning":[54,117,134],"setting":[55],"evaluates":[57],"these":[58],"models":[59,77],"using":[60,173],"ground-truth":[61],"future":[62],"observations":[63],"as":[64],"goals,":[65],"without":[66,198],"training":[67,149],"any":[68,150],"policy.":[70],"We":[71],"find":[72],"JEPA-based":[75],"are":[78],"either":[79],"accurate":[80],"but":[83,89],"computationally":[84,87],"expensive,":[85],"or":[86],"efficient":[88],"insufficient":[90],"planning.":[92,203],"address":[94],"trade-off,":[96],"propose":[98],"\\textbf{AD-E2E-JEPA},":[99],"which":[100],"introduces":[101],"SIGReg-regularized":[103],"learnable":[104],"projector":[105,112,211],"applied":[106],"to":[107,219],"projected":[108],"patch":[109],"embeddings.":[110],"The":[111,222],"reduces":[113],"number":[115],"of":[116,169,179],"patches":[118],"by":[119,125],"$16\\times$":[120],"embedding":[123],"dimension":[124],"$4\\times$,":[126],"achieving":[127],"$100\\times$":[129],"inference":[130],"speedup":[131],"while":[132],"retaining":[133],"performance,":[135],"with":[136,191],"0.8-second":[138],"runtime":[139],"an":[141],"8-frame":[142],"rollout":[143],"over":[144,176],"256":[145],"candidate":[146],"trajectories.":[147],"\\textit{Without}":[148],"policy,":[152],"model":[155],"itself":[156],"reaches":[157],"goals":[159],"located":[160],"20":[161],"meters":[162],"away":[163],"on":[164],"average":[165],"within":[166],"displacement":[168],"respectively":[170,180],"4.0/2.8":[171],"meters,":[172],"rollouts":[175],"trajectory":[177],"vocabularies":[178],"256/8,192":[181],"candidates.":[182],"On":[183],"NAVSIMv2":[185],"benchmark,":[186],"it":[187],"achieves":[188],"67.3/72.9":[189],"EPDMS":[190],"multiplicative":[192],"safety":[193],"metrics":[194],"84.1/86.5":[196],"EPDMS$^{\\dagger}$":[197],"them":[199],"in":[200],"Experiments":[204],"further":[205],"show":[206],"self-supervised":[209],"pretrained":[210],"improves":[212],"downstream":[213],"imitation":[214],"learning":[215],"performance":[216],"80.2":[218],"85.4":[220],"EPDMS.":[221],"source":[223],"code":[224],"is":[225],"available":[226],"at":[227],"https://github.com/HaoranZhuExplorer/AD-E2E-JEPA":[228]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}