{"id":"https://openalex.org/W4417135147","doi":"https://doi.org/10.1109/iccv51701.2025.02462","title":"ETA: Efficiency through Thinking Ahead, a Dual Approach to Self-Driving with Large Models","display_name":"ETA: Efficiency through Thinking Ahead, a Dual Approach to Self-Driving with Large Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417135147","doi":"https://doi.org/10.1109/iccv51701.2025.02462"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.07725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107513531","display_name":"Shadi Hamdan","orcid":"https://orcid.org/0000-0002-8966-2347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shadi Hamdan","raw_affiliation_strings":["Koç University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koç University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120725794","display_name":"Chonghao Sima","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chonghao Sima","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zetong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136907","display_name":"InternetLab","ror":"https://ror.org/04a7qxt37","country_code":"BR","type":"facility","lineage":["https://openalex.org/I4210136907"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zetong Yang","raw_affiliation_strings":["OpenDriveLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenDriveLab","institution_ids":["https://openalex.org/I4210136907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450549","display_name":"Hongyang Li","orcid":"https://orcid.org/0000-0001-5891-134X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongyang Li","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083242590","display_name":"Fatma G\u00fcney","orcid":"https://orcid.org/0000-0002-0358-983X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fatma G\u00fcney","raw_affiliation_strings":["Koç University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koç University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"26529","last_page":"26538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.36570000648498535,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.36570000648498535,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11680000275373459,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10869999974966049,"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/inference","display_name":"Inference","score":0.79339998960495},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6898000240325928},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5411999821662903},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.501800000667572},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.49959999322891235},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45660001039505005},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.4212999939918518},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.40470001101493835}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.79339998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735000252723694},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46480000019073486},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.07725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07725","pdf_url":"https://arxiv.org/pdf/2506.07725","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.07725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.07725","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":"pmh:oai:arXiv.org:2506.07725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07725","pdf_url":"https://arxiv.org/pdf/2506.07725","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5113843979","display_name":null,"funder_award_id":"62206172","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2,126],"benefit":[3],"from":[4,65,142,152],"large":[5,57,77,114,154],"models":[6,78,115],"without":[7],"sacrificing":[8],"inference":[9,50,68,107,207],"speed,":[10],"a":[11,21,25,33,80,105,162,198,205],"common":[12],"dilemma":[13],"in":[14],"self-driving":[15],"systems?":[16],"A":[17],"prevalent":[18],"solution":[19],"is":[20,51,90],"dual-system":[22,43],"architecture,":[23],"employing":[24],"small":[26,163],"model":[27,35,58,164],"for":[28,36,79,165],"rapid,":[29],"reactive":[30],"decisions":[31],"and":[32,103,168],"larger":[34],"slower":[37],"but":[38],"more":[39],"informative":[40,140],"analyses.":[41],"Existing":[42],"designs":[44],"often":[45],"implement":[46],"parallel":[47],"architectures":[48],"where":[49],"either":[52],"directly":[53],"conducted":[54],"using":[55,149,161],"the":[56,96,124,143,146,153,186],"at":[59,209],"each":[60,119],"current":[61,97,147,158],"frame":[62,98,148,159],"or":[63],"retrieved":[64],"previously":[66],"stored":[67],"results.":[69],"However,":[70],"these":[71,171],"works":[72],"still":[73],"struggle":[74],"to":[75,83,91,99,112,118,145],"enable":[76],"timely":[81],"response":[82],"every":[84],"online":[85],"frame.":[86],"Our":[87],"key":[88],"insight":[89],"shift":[92],"intensive":[93],"computations":[94],"of":[95,108,201],"previous":[100],"time":[101,110,120],"steps":[102,111],"perform":[104],"batch":[106],"multiple":[109],"make":[113],"respond":[116],"promptly":[117],"step.":[121],"To":[122],"achieve":[123],"shifting,":[125],"introduce":[127],"Efficiency":[128],"through":[129],"Thinking":[130],"Ahead":[131],"(ETA),":[132],"an":[133,175],"asynchronous":[134],"system":[135],"designed":[136],"to:":[137],"(1)":[138],"propagate":[139],"features":[141,160,173],"past":[144],"future":[150],"predictions":[151],"model,":[155],"(2)":[156],"extract":[157],"real-time":[166],"responsiveness,":[167],"(3)":[169],"integrate":[170],"dual":[172],"via":[174],"action":[176],"mask":[177],"mechanism":[178],"that":[179],"emphasizes":[180],"action-critical":[181],"image":[182],"regions.":[183],"Evaluated":[184],"on":[185],"Bench2Drive":[187],"CARLA":[188],"Leaderboard-v2":[189],"benchmark,":[190],"ETA":[191],"advances":[192],"state-of-the-art":[193],"performance":[194],"by":[195],"8%":[196],"with":[197],"driving":[199],"score":[200],"69.53":[202],"while":[203],"maintaining":[204],"near-real-time":[206],"speed":[208],"50":[210],"ms.":[211]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}