{"id":"https://openalex.org/W7163353631","doi":"https://doi.org/10.48550/arxiv.2606.03847","title":"Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies","display_name":"Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163353631","doi":"https://doi.org/10.48550/arxiv.2606.03847"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03847","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.2606.03847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137805233","display_name":"Xiangdong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xiangdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137790582","display_name":"Yuxuan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137761674","display_name":"Chen Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137733146","display_name":"Boyao Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Boyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010768718","display_name":"Yuxuan Yan","orcid":"https://orcid.org/0009-0004-2803-738X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121922700","display_name":"Yitong Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Yitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137774554","display_name":"Zhuotao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Zhuotao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137747934","display_name":"Li Jiang (120930)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Li","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42399999499320984,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42399999499320984,"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":0.28700000047683716,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.025100000202655792,"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/robot","display_name":"Robot","score":0.5509999990463257},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.519599974155426},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5005000233650208},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4846000075340271},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4690999984741211},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4230000078678131},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4690999984741211},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4472000002861023},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03847","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.2606.03847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03847","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Action":[0],"chunking":[1],"has":[2],"become":[3],"a":[4,96,148,175],"common":[5],"inference":[6],"strategy":[7],"for":[8],"flow-based":[9,60],"robot":[10],"policies,":[11],"improving":[12,201],"action":[13],"coherence":[14],"by":[15,87,189],"modeling":[16],"multi-step":[17],"temporal":[18],"dependencies":[19],"in":[20],"demonstrations.":[21],"However,":[22],"the":[23,56,113,119,124,145,152],"execution":[24,203],"horizon":[25],"is":[26],"still":[27],"typically":[28],"set":[29],"as":[30],"an":[31,63],"empirical":[32],"fixed":[33],"value,":[34],"overlooking":[35],"that":[36,55,99,165],"predictable":[37,74],"free-space":[38],"motions":[39],"and":[40,128,140,161,186,198,200],"precision-critical":[41],"interaction":[42],"phases":[43],"often":[44],"require":[45],"different":[46],"replanning":[47,172,188],"frequencies.":[48],"In":[49],"this":[50,88],"work,":[51],"we":[52,90],"first":[53],"show":[54,164],"denoising":[57,121],"process":[58],"of":[59,66,115,151],"policies":[61],"contains":[62],"intrinsic":[64],"signal":[65],"task":[67,168],"phases:":[68],"clean-action":[69,116],"estimates":[70,117],"remain":[71],"stable":[72,125],"during":[73],"motion":[75],"phases,":[76],"but":[77],"fluctuate":[78],"more":[79],"strongly":[80],"around":[81],"contact-rich":[82],"or":[83],"precision-sensitive":[84],"operations.":[85],"Motivated":[86],"observation,":[89],"propose":[91],"DVAC":[92,111,142,166,178],"(Denoising-Variance":[93],"Adaptive":[94],"Chunking),":[95],"test-time":[97],"method":[98],"adaptively":[100],"determines":[101],"how":[102],"many":[103],"actions":[104,133],"to":[105,184],"execute":[106],"from":[107,182],"each":[108],"predicted":[109],"chunk.":[110],"measures":[112],"variance":[114,154],"over":[118],"final":[120],"steps,":[122],"executes":[123],"low-variance":[126],"prefix,":[127],"replans":[129],"before":[130],"high-variance":[131],"future":[132],"are":[134],"committed.":[135],"To":[136],"transfer":[137],"across":[138],"tasks":[139],"rollouts,":[141],"further":[143],"calibrates":[144],"threshold":[146],"with":[147],"rolling":[149],"estimate":[150],"local":[153],"scale.":[155],"Experiments":[156],"on":[157,196],"LIBERO,":[158],"RoboTwin,":[159],"CALVIN,":[160],"real-world":[162,202],"manipulation":[163],"improves":[167,179],"success":[169,181],"while":[170,191],"reducing":[171],"frequency.":[173],"With":[174],"$\u03c0_{0.5}$-based":[176],"policy,":[177],"LIBERO":[180],"94.75%":[183],"98.00%":[185],"reduces":[187],"43.0%,":[190],"also":[192],"yielding":[193],"aggregate":[194],"gains":[195],"RoboTwin":[197],"CALVIN":[199],"efficiency.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}