{"id":"https://openalex.org/W7139128435","doi":"https://doi.org/10.1609/aaai.v40i40.40737","title":"V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision Transformer","display_name":"V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision Transformer","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7139128435","doi":"https://doi.org/10.1609/aaai.v40i40.40737"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i40.40737","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40737","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i40.40737","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guangzhen Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhen Yao","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayun Zheng","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zezhou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zezhou Wang","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenxin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Zhang","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Renda Han","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renda Han","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuangxin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuangxin Zhao","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":null,"display_name":"Runhao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhao Liu","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98431049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"40","first_page":"34396","last_page":"34404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.27239999175071716,"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":0.27239999175071716,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.14319999516010284,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.13189999759197235,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7789000272750854},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7024999856948853},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6065000295639038},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5486000180244446},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3977999985218048},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.322299987077713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982000112533569},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7789000272750854},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7024999856948853},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5285999774932861},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i40.40737","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40737","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"},{"id":"pmh:oai:ojs.aaai.org:article/40737","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i40.40737","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40737","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0,109],"Transformer":[1],"(ViT)":[2],"has":[3],"become":[4],"one":[5],"of":[6,9,71,121,179],"the":[7,10,68,78,88,176],"cornerstones":[8],"computer":[11],"vision":[12],"field,":[13],"demonstrating":[14],"exceptional":[15],"performance.":[16,187,219],"However,":[17,50],"its":[18],"inherent":[19],"high":[20],"computational":[21,48,168],"complexity":[22],"and":[23,74,103,167,194,208],"inference":[24,206],"latency":[25],"still":[26],"pose":[27],"significant":[28],"obstacles":[29],"for":[30,108,129],"deployment":[31],"in":[32,217],"resource-constrained":[33],"environments.":[34],"Token":[35],"pruning,":[36],"by":[37],"removing":[38],"less":[39],"informative":[40],"tokens,":[41],"offers":[42],"an":[43,118],"effective":[44],"strategy":[45],"to":[46,76,116,170],"reduce":[47],"overhead.":[49],"existing":[51,212],"pruning":[52,72,82,106,130,148,181,215],"methods":[53],"largely":[54],"rely":[55],"on":[56,133,184,190],"static":[57],"or":[58],"local":[59],"token":[60,105,122,147],"importance":[61],"scores.":[62],"This":[63],"myopic":[64],"approach":[65],"fundamentally":[66],"overlooks":[67],"sequential":[69,152],"dependency":[70],"decisions":[73,83],"fails":[75],"capture":[77],"interaction":[79],"effects":[80],"between":[81,91,203],"across":[84],"layers,":[85],"often":[86],"neglecting":[87],"global":[89,151,185],"interactions":[90],"mask":[92],"variables.":[93],"To":[94],"address":[95],"this":[96],"limitation,":[97],"we":[98],"propose":[99],"V-Pruner,":[100],"a":[101,125,137,150,158,200],"fast":[102],"globally-informed":[104],"framework":[107],"Transformer.":[110],"V-Pruner":[111,135,198],"first":[112],"leverages":[113],"Fisher":[114],"information":[115],"perform":[117],"initial":[119,127],"assessment":[120],"importance,":[123],"providing":[124],"principled":[126],"prior":[128],"decisions.":[131],"Building":[132],"this,":[134],"introduces":[136],"Reinforcement":[138],"Learning":[139],"(RL)":[140],"Proximal":[141],"Policy":[142],"Optimization":[143],"(PPO)":[144],"algorithm,":[145],"refining":[146],"into":[149],"decision":[153,182],"process.":[154],"The":[155],"algorithm":[156],"combines":[157],"composite":[159],"reward":[160],"signal":[161],"that":[162,197],"incorporates":[163],"both":[164],"model":[165,186],"performance":[166],"cost":[169],"guide":[171],"policy":[172],"exploration,":[173],"effectively":[174],"evaluating":[175],"long-term":[177],"impact":[178],"different":[180],"combinations":[183],"Extensive":[188],"experiments":[189],"ViT-L,":[191],"DeiT-B,":[192],"DeiT-S,":[193],"DeiT-T":[195],"demonstrate":[196],"achieves":[199],"better":[201],"balance":[202],"accuracy,":[204],"GFLOPs,":[205],"speed,":[207],"training":[209],"time,":[210],"surpassing":[211],"mainstream":[213],"ViT":[214],"algorithms":[216],"overall":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-02T00:00:00"}