{"id":"https://openalex.org/W7138407488","doi":"https://doi.org/10.1609/aaai.v40i4.37244","title":"FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning","display_name":"FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138407488","doi":"https://doi.org/10.1609/aaai.v40i4.37244"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i4.37244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37244","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i4.37244","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129721974","display_name":"Jiajun Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733493","display_name":"Qizhe Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qizhe Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648327","display_name":"Peidong Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peidong Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669348","display_name":"Xuhui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuhui Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713429","display_name":"Bo Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128790168","display_name":"Xiaoan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681885","display_name":"Lizhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lizhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650073","display_name":"Xiaobao Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobao Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683562","display_name":"Sixiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sixiang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129658934","display_name":"Liyun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liyun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741397","display_name":"Xianming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianming Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129709628","display_name":"Ming Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725656","display_name":"Yang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129734509","display_name":"Shanghang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanghang Zhang","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":5.9578,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95535082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"4","first_page":"2571","last_page":"2579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9101999998092651,"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":0.9101999998092651,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.027499999850988388,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02199999988079071,"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/security-token","display_name":"Security token","score":0.7734000086784363},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7484999895095825},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6241999864578247},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5544000267982483},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.3718000054359436},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821999788284302},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7734000086784363},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7484999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6678000092506409},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4634999930858612},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i4.37244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37244","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37244","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5863727927207947,"display_name":"Peace, Justice and strong institutions"}],"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":[2,31,153],"have":[3,56],"demonstrated":[4],"significant":[5],"potential":[6],"in":[7,19,41,60],"complex":[8],"scene":[9],"understanding":[10],"and":[11],"action":[12],"reasoning,":[13],"leading":[14],"to":[15,133,150],"their":[16],"increasing":[17],"adoption":[18],"end-to-end":[20],"autonomous":[21,61,106],"driving":[22,62],"systems.":[23],"However,":[24],"the":[25,137,155,187],"long":[26],"visual":[27,37,48,79,112,138,157],"tokens":[28,80],"of":[29,140,173],"VLA":[30,141,152],"greatly":[32],"increase":[33],"computational":[34],"costs.":[35],"Current":[36],"token":[38,49,100,113],"pruning":[39,101,194],"methods":[40],"Vision-Language":[42],"Models":[43],"(VLM)":[44],"rely":[45],"on":[46,69,186],"either":[47],"similarity":[50],"or":[51],"visual-text":[52],"attention,":[53],"but":[54],"both":[55],"shown":[57],"poor":[58],"performance":[59],"scenarios.":[63],"Given":[64],"that":[65,77],"human":[66],"drivers":[67],"concentrate":[68],"relevant":[70],"foreground":[71,83,119,179],"areas":[72],"while":[73],"driving,":[74],"we":[75,93,164],"assert":[76],"retaining":[78],"containing":[81],"this":[82],"information":[84,120],"is":[85,131],"essential":[86],"for":[87,105,136],"effective":[88],"decision-making.":[89],"Inspired":[90],"by":[91],"this,":[92],"propose":[94],"FastDriveVLA,":[95],"a":[96,110,167],"novel":[97,126],"reconstruction-based":[98],"vision":[99],"framework":[102],"designed":[103,132],"specifically":[104],"driving.":[107],"FastDriveVLA":[108],"includes":[109],"plug-and-play":[111],"pruner":[114],"called":[115,170],"ReconPruner,":[116,163],"which":[117],"prioritizes":[118],"through":[121],"MAE-style":[122],"pixel":[123],"reconstruction.":[124],"A":[125],"adversarial":[127],"foreground-background":[128],"reconstruction":[129],"strategy":[130],"train":[134,162],"ReconPruner":[135,145],"encoder":[139,158],"models.":[142],"Once":[143],"trained,":[144],"can":[146],"be":[147],"seamlessly":[148],"applied":[149],"different":[151,193],"with":[154,177],"same":[156],"without":[159],"retraining.":[160],"To":[161],"also":[165],"introduce":[166],"large-scale":[168],"dataset":[169],"nuScenes-FG,":[171],"consisting":[172],"241K":[174],"image-mask":[175],"pairs":[176],"annotated":[178],"regions.":[180],"Our":[181],"approach":[182],"achieves":[183],"state-of-the-art":[184],"results":[185],"nuScenes":[188],"open-loop":[189],"planning":[190],"benchmark":[191],"across":[192],"ratios.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}