{"id":"https://openalex.org/W7139919713","doi":"https://doi.org/10.48550/arxiv.2603.18342","title":"Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model","display_name":"Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7139919713","doi":"https://doi.org/10.48550/arxiv.2603.18342"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18342","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003914203","display_name":"Yanchuan Tang","orcid":"https://orcid.org/0000-0002-8114-5871"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Yanchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130227509","display_name":"Taowen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Taowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130216116","display_name":"Yuefei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuefei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102905597","display_name":"Boxuan Zhang","orcid":"https://orcid.org/0000-0001-5673-8774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Boxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130215934","display_name":"Qiang Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130234164","display_name":"Ruixiang Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ruixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003914203"],"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":0.4961000084877014,"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":0.4961000084877014,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.11309999972581863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.06120000034570694,"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/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.7107999920845032},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6735000014305115},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6351000070571899},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6280999779701233},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5415999889373779},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.531499981880188},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.486299991607666},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.4251999855041504}],"concepts":[{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.7107999920845032},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6735000014305115},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291000247001648},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4625000059604645},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.4251999855041504},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.37790000438690186},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C176147448","wikidata":"https://www.wikidata.org/wiki/Q1889114","display_name":"Sensitivity analysis","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18342","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18342","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4268247187137604,"display_name":"Peace, Justice and strong institutions"}],"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],"enable":[3],"general-purpose":[4],"robotic":[5],"policies":[6],"by":[7],"mapping":[8],"visual":[9],"observations":[10],"and":[11,33,78,127,154],"language":[12],"instructions":[13],"to":[14,27,63,108,118,135],"low-level":[15],"actions,":[16],"but":[17,46],"they":[18],"often":[19],"lack":[20],"reliable":[21,157],"introspection.":[22],"A":[23],"common":[24],"practice":[25],"is":[26],"compute":[28],"a":[29,38,90],"token-level":[30],"uncertainty":[31,48,92],"signal":[32],"take":[34],"its":[35],"mean":[36,41],"over":[37],"rollout.":[39],"However,":[40],"aggregation":[42],"can":[43,72,163],"dilute":[44],"short-lived":[45],"safety-critical":[47],"spikes":[49,82],"in":[50],"continuous":[51],"control.":[52],"In":[53],"particular,":[54],"successful":[55],"rollouts":[56,71],"may":[57],"contain":[58],"localized":[59],"high-entropy":[60],"segments":[61],"due":[62],"benign":[64],"noise":[65],"or":[66],"non-critical":[67],"micro-adjustments,":[68],"while":[69],"failure":[70,100,151,160],"appear":[73],"low-entropy":[74],"for":[75,95,159],"most":[76],"timesteps":[77],"only":[79],"exhibit":[80],"brief":[81],"near":[83],"the":[84,142],"onset":[85],"of":[86],"failure.":[87],"We":[88],"propose":[89],"unified":[91],"quantification":[93],"approach":[94],"predicting":[96],"rollout":[97],"success":[98],"versus":[99],"that":[101,146],"(1)":[102],"uses":[103],"max-based":[104],"sliding":[105],"window":[106],"pooling":[107],"preserve":[109],"transient":[110],"risk":[111],"signals,":[112],"(2)":[113],"applies":[114],"motion-aware":[115],"stability":[116],"weighting":[117],"emphasize":[119],"high-frequency":[120],"action":[121],"oscillations":[122],"associated":[123],"with":[124],"unstable":[125],"behaviors,":[126],"(3)":[128],"performs":[129],"DoF-adaptive":[130],"calibration":[131],"via":[132],"Bayesian":[133],"Optimization":[134],"prioritize":[136],"kinematically":[137],"critical":[138],"axes.":[139],"Experiments":[140],"on":[141],"LIBERO":[143],"benchmark":[144],"show":[145],"our":[147],"method":[148],"substantially":[149],"improves":[150],"prediction":[152],"accuracy":[153],"yields":[155],"more":[156],"signals":[158],"detection,":[161],"which":[162],"support":[164],"downstream":[165],"human-in-the-loop":[166],"interventions.":[167]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-21T00:00:00"}