{"id":"https://openalex.org/W7163066416","doi":"https://doi.org/10.48550/arxiv.2605.31116","title":"NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving","display_name":"NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163066416","doi":"https://doi.org/10.48550/arxiv.2605.31116"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31116","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.31116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137585547","display_name":"Jiahui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137597189","display_name":"Jiawei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087463599","display_name":"Zixiang Ren","orcid":"https://orcid.org/0000-0003-1626-9605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Zixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137608655","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0001-7812-6664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137589248","display_name":"Jiamin Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jiamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111258616","display_name":"Ruiteng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ruiteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137583385","display_name":"Zhiyang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137516554","display_name":"Liying Liu","orcid":"https://orcid.org/0000-0002-0637-7488"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Liying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127825890","display_name":"Zuoguan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zuoguan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137607211","display_name":"Kaidi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Kaidi","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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.27889999747276306,"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":0.27889999747276306,"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":0.2345000058412552,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.10989999771118164,"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/bottleneck","display_name":"Bottleneck","score":0.7491000294685364},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5942999720573425},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49300000071525574},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.43950000405311584},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3968999981880188},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.37770000100135803},{"id":"https://openalex.org/keywords/rapid-serial-visual-presentation","display_name":"Rapid serial visual presentation","score":0.37770000100135803},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3772999942302704},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.36579999327659607}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7491000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6342999935150146},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5920000076293945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31116","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.31116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31116","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7119791507720947}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"perception-free":[1,77],"end-to-end":[2],"(E2E)":[3],"autonomous":[4,171],"driving":[5,172],"methods":[6],"bypass":[7],"explicit":[8,147],"perception":[9,148],"outputs":[10],"by":[11],"compressing":[12],"dense":[13],"image":[14],"patch":[15],"tokens":[16,20,30,97,114,191],"into":[17],"compact":[18,33,73,95,207],"scene":[19,29,96,113,190],"for":[21,36,123],"downstream":[22],"trajectory":[23],"generation":[24],"and":[25,118,180,196,211],"scoring.":[26],"While":[27],"these":[28],"form":[31],"a":[32,65,81,135],"visual":[34,53,121,208],"bottleneck":[35,75,203],"the":[37,44,51,72,109,160],"planner,":[38],"they":[39],"receive":[40],"supervision":[41,204],"solely":[42],"from":[43,131],"planning":[45,212],"objective,":[46],"providing":[47],"limited":[48],"constraints":[49],"on":[50,168,177,186],"encoded":[52],"information.":[54],"To":[55],"address":[56],"this":[57],"limitation,":[58],"we":[59],"introduce":[60,127],"Neural":[61],"Token":[62],"Reconstruction":[63],"(NTR),":[64],"representation":[66,209],"learning":[67,210],"framework":[68],"to":[69,105,115],"directly":[70],"constrain":[71],"scene-token":[74,110],"in":[76],"driving.":[78],"NTR":[79,164],"introduces":[80],"self-distillation":[82],"masked":[83,89],"latent":[84,91],"reconstruction":[85,99,103,140,152],"objective":[86],"that":[87,201],"reconstructs":[88],"patch-level":[90],"features":[92],"using":[93],"only":[94],"as":[98,134],"memory.":[100],"This":[101],"forces":[102],"gradients":[104],"pass":[106],"exclusively":[107],"through":[108],"bottleneck,":[111],"encouraging":[112],"preserve":[116],"richer":[117],"less":[119],"redundant":[120],"representations":[122],"planning.":[124],"We":[125],"further":[126],"semantic":[128,137],"priors":[129],"derived":[130],"foundation-model":[132],"annotations":[133],"weak":[136],"interface":[138],"biasing":[139],"targets":[141],"toward":[142],"driving-related":[143],"structures":[144],"without":[145],"introducing":[146],"heads.":[149],"All":[150],"auxiliary":[151],"components":[153],"are":[154],"removed":[155],"at":[156],"inference":[157],"time,":[158],"leaving":[159],"deployed":[161],"planner":[162],"unchanged.":[163],"achieves":[165],"state-of-the-art":[166],"performance":[167],"three":[169],"public":[170],"benchmarks,":[173],"including":[174],"8.0461":[175],"RFS":[176],"Waymo":[178],"E2E":[179],"94.1":[181],"PDMS":[182],"/":[183],"90.9":[184],"EPDMS":[185],"NavSim1&2.":[187],"The":[188],"learned":[189],"exhibit":[192],"lower":[193],"pairwise":[194],"redundancy":[195],"higher":[197],"effective":[198,202],"rank,":[199],"indicating":[200],"improves":[205],"both":[206],"performance.":[213]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}