{"id":"https://openalex.org/W7140296076","doi":"https://doi.org/10.48550/arxiv.2603.22991","title":"VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models","display_name":"VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140296076","doi":"https://doi.org/10.48550/arxiv.2603.22991"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22991","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22991","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":null,"license_id":null,"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.2603.22991","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130624473","display_name":"Jintao Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Jintao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130619793","display_name":"Haozhe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haozhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130570416","display_name":"Weibin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130560494","display_name":"Gang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Gang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130545776","display_name":"Yipu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yipu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130621596","display_name":"Xiaoyu Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130548044","display_name":"Jin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130543895","display_name":"Xieyuanli Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xieyuanli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130597999","display_name":"Yunhui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yunhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130550238","display_name":"Wei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9732999801635742,"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":0.9732999801635742,"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":0.006000000052154064,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6362000107765198},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6029000282287598},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49320000410079956},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4742000102996826},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4316999912261963},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3824999928474426},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998999953269958},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6362000107765198},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.3059000074863434},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22991","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22991","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.22991","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22991","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"rapidly":[4],"advanced":[5],"embodied":[6],"intelligence,":[7],"enabling":[8],"robots":[9],"to":[10,80,111,164,171],"execute":[11],"complex,":[12],"instruction-driven":[13],"tasks.":[14,64],"However,":[15],"as":[16,192,194],"model":[17,185],"capacity":[18],"and":[19,115,138,162,180,187,204],"visual":[20,41],"context":[21],"length":[22],"grow,":[23],"the":[24,55,159,172,176],"inference":[25],"cost":[26],"of":[27,62],"VLA":[28,63],"systems":[29],"becomes":[30],"a":[31,59,92,107,116,130,150,155,195],"major":[32],"bottleneck":[33],"for":[34],"real-world":[35],"deployment":[36],"on":[37,47,125,158],"resource-constrained":[38],"platforms.":[39],"Existing":[40],"token":[42],"pruning":[43,122],"methods":[44],"mainly":[45],"rely":[46],"semantic":[48],"saliency":[49],"or":[50],"simple":[51],"temporal":[52],"cues,":[53],"overlooking":[54],"continuous":[56],"physical":[57],"interaction,":[58],"fundamental":[60],"property":[61],"Consequently,":[65],"current":[66],"approaches":[67],"often":[68],"prune":[69],"visually":[70],"sparse":[71],"yet":[72],"structurally":[73],"critical":[74],"regions":[75],"that":[76,120,147],"support":[77],"manipulation,":[78],"leading":[79],"unstable":[81],"behavior":[82],"during":[83,135],"early":[84,136],"task":[85],"phases.":[86],"To":[87],"overcome":[88],"this,":[89],"we":[90],"propose":[91],"shift":[93],"toward":[94],"an":[95],"explicit":[96],"Interaction-First":[97],"paradigm.":[98],"Our":[99,207],"proposed":[100],"\\textbf{training-free}":[101],"method,":[102],"VLA-IAP":[103,148],"(Interaction-Aligned":[104],"Pruning),":[105],"introduces":[106],"geometric":[108],"prior":[109],"mechanism":[110],"preserve":[112],"structural":[113],"anchors":[114],"dynamic":[117],"scheduling":[118],"strategy":[119],"adapts":[121],"intensity":[123],"based":[124],"semantic-motion":[126],"alignment.":[127],"This":[128],"enables":[129],"conservative-to-aggressive":[131],"transition,":[132],"ensuring":[133],"robustness":[134],"uncertainty":[137],"efficiency":[139],"once":[140],"interaction":[141],"is":[142],"locked.":[143],"Extensive":[144],"experiments":[145],"show":[146],"achieves":[149],"\\textbf{97.8\\%":[151],"success":[152],"rate}":[153],"with":[154],"\\textbf{$1.25\\times$":[156],"speedup}":[157,166],"LIBERO":[160],"benchmark,":[161],"up":[163],"\\textbf{$1.54\\times$":[165],"while":[167],"maintaining":[168],"performance":[169,182],"\\textbf{comparable":[170],"unpruned":[173],"backbone}.":[174],"Moreover,":[175],"method":[177],"demonstrates":[178],"superior":[179],"consistent":[181],"across":[183],"multiple":[184],"architectures":[186],"three":[188],"different":[189],"simulation":[190],"environments,":[191],"well":[193],"real":[196],"robot":[197],"platform,":[198],"validating":[199],"its":[200],"strong":[201],"generalization":[202],"capability":[203],"practical":[205],"applicability.":[206],"project":[208],"website":[209],"is:":[210],"\\href{https://chengjt1999.github.io/VLA-IAP.github.io/}{VLA-IAP.com}.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-26T00:00:00"}