{"id":"https://openalex.org/W7160254586","doi":"https://doi.org/10.48550/arxiv.2605.01194","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","display_name":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7160254586","doi":"https://doi.org/10.48550/arxiv.2605.01194"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01194","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01194","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.01194","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135335496","display_name":"Wenhao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135403641","display_name":"Xiu Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Xiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020944070","display_name":"Dan Niu","orcid":"https://orcid.org/0000-0002-0715-7946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135297145","display_name":"Yichao Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hongyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135371616","display_name":"Hongyan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Xiaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135347451","display_name":"Zhe Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Shan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135383456","display_name":"Lei Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135373697","display_name":"Shan You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.8306000232696533,"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":0.8306000232696533,"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":0.015799999237060547,"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":0.013700000010430813,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5777000188827515},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.520799994468689},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5159000158309937},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.38839998841285706},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3815999925136566},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.32710000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495000123977661},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01194","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01194","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01194","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01194","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8290331959724426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,54],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"and":[7,123,158],"generalization":[8],"in":[9],"embodied":[10],"manipulation.":[11],"However,":[12],"their":[13],"decision-making":[14],"relies":[15],"on":[16],"a":[17,49,73,82],"fast,":[18],"instinctive":[19],"process":[20],"that":[21,39,51,128],"lacks":[22],"deliberation.":[23],"This":[24,99],"strategy":[25,118],"often":[26],"leads":[27],"to":[28,66,72,119],"suboptimal":[29],"or":[30,36],"catastrophic":[31],"actions":[32],"when":[33,77],"facing":[34],"complex":[35],"ambiguous":[37],"scenarios":[38],"require":[40],"greater":[41],"consideration.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,113],"introduce":[47,114],"\\textbf{VLA-ATTC},":[48],"framework":[50],"endows":[52],"VLA":[53],"with":[55],"adaptive":[56],"test-time":[57],"compute":[58],"(TTC).":[59],"VLA-ATTC":[60,139],"employs":[61],"an":[62,115,124],"uncertainty-based":[63],"``cognitive":[64],"clutch''":[65],"dynamically":[67],"transition":[68],"from":[69,93],"reflexive":[70],"execution":[71],"TTC":[74,80],"deliberation":[75],"phase":[76],"necessary.":[78],"During":[79],"phase,":[81],"novel":[83],"\\textbf{Relative":[84],"Action":[85],"Critic}":[86],"(RAC)":[87],"model":[88,147],"identifies":[89],"the":[90,109,136,141,145,156],"optimal":[91],"action":[92],"generated":[94],"candidates":[95],"via":[96],"pairwise":[97],"comparisons.":[98],"relative":[100],"mechanism":[101],"replaces":[102],"unstable":[103],"absolute":[104],"value":[105],"estimation,":[106],"significantly":[107],"simplifying":[108],"learning":[110],"objective.":[111],"Furthermore,":[112],"efficient":[116],"sampling":[117],"amortize":[120],"computational":[121],"costs":[122],"automated":[125],"data":[126],"pipeline":[127],"curates":[129],"preference":[130],"pairs":[131],"without":[132],"manual":[133],"annotation.":[134],"On":[135],"LIBERO-LONG":[137],"benchmark,":[138],"reduces":[140],"failure":[142],"rate":[143],"of":[144],"SOTA":[146],"PI0.5":[148],"by":[149],"over":[150],"50\\%.":[151],"We":[152],"will":[153],"open-source":[154],"all":[155],"code":[157],"weights.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}