{"id":"https://openalex.org/W7151252330","doi":"https://doi.org/10.48550/arxiv.2604.04161","title":"Adaptive Action Chunking at Inference-time for Vision-Language-Action Models","display_name":"Adaptive Action Chunking at Inference-time for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-04-05","ids":{"openalex":"https://openalex.org/W7151252330","doi":"https://doi.org/10.48550/arxiv.2604.04161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04161","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.2604.04161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102693316","display_name":"Yuanchang Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yuanchang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133106411","display_name":"Xiaobo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133140841","display_name":"Kai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133089167","display_name":"Shuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133133252","display_name":"Xiaojiang Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Xiaojiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133117173","display_name":"Haoyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109165176","display_name":"David Kim Huat Chua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chua, David Kim Huat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053670340","display_name":"Prahlad Vadakkepat","orcid":"https://orcid.org/0000-0003-2649-9893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vadakkepat, Prahlad","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":0.5467000007629395,"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":0.5467000007629395,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.21279999613761902,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05249999836087227,"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/chunking","display_name":"Chunking (psychology)","score":0.7408999800682068},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6004999876022339},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5651999711990356},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4099999964237213},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3968999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079000115394592},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7408999800682068},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.31859999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04161","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.2604.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04161","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"Vision-Language-Action":[1],"(VLA)":[2],"models,":[3],"action":[4,109],"chunking":[5],"(i.e.,":[6],"executing":[7],"a":[8,16,25,37,70,100,127],"sequence":[9],"of":[10,43,130],"actions":[11],"without":[12],"intermediate":[13],"replanning)":[14],"is":[15,58,77],"key":[17],"technique":[18],"to":[19,33,62,114],"improve":[20],"robotic":[21,134],"manipulation":[22,92,135],"abilities.":[23],"However,":[24],"large":[26],"chunk":[27,56,81,118],"size":[28,57,119],"reduces":[29],"the":[30,41,54,64,112,117,146],"model's":[31,65],"responsiveness":[32],"new":[34],"information,":[35],"while":[36],"small":[38],"one":[39],"increases":[40],"likelihood":[42],"mode-jumping,":[44],"jerky":[45],"behavior":[46],"resulting":[47],"from":[48],"discontinuities":[49],"between":[50],"chunks.":[51],"Therefore,":[52],"selecting":[53],"optimal":[55],"an":[59,78],"urgent":[60],"demand":[61],"balance":[63],"reactivity":[66],"and":[67,88,132,151],"consistency.":[68],"Unfortunately,":[69],"dominant":[71],"trend":[72],"in":[73],"current":[74,122],"VLA":[75],"models":[76],"empirical":[79],"fixed":[80],"length":[82],"at":[83,157],"inference-time,":[84],"hindering":[85],"their":[86],"superiority":[87],"scalability":[89],"across":[90],"diverse":[91],"tasks.":[93],"To":[94],"address":[95],"this":[96],"issue,":[97],"we":[98],"propose":[99],"novel":[101],"Adaptive":[102],"Action":[103],"Chunking":[104],"(AAC)":[105],"strategy,":[106],"which":[107],"exploits":[108],"entropy":[110],"as":[111],"cue":[113],"adaptively":[115],"determine":[116],"based":[120],"on":[121,126],"predictions.":[123],"Extensive":[124],"experiments":[125],"wide":[128],"range":[129],"simulated":[131],"real-world":[133],"tasks":[136],"have":[137],"demonstrated":[138],"that":[139],"our":[140],"approach":[141],"substantially":[142],"improves":[143],"performance":[144],"over":[145],"state-of-the-art":[147],"alternatives.":[148],"The":[149],"videos":[150],"source":[152],"code":[153],"are":[154],"publicly":[155],"available":[156],"https://lance-lot.github.io/adaptive-chunking.github.io/.":[158]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}