{"id":"https://openalex.org/W7129063177","doi":"https://doi.org/10.48550/arxiv.2602.12978","title":"Learning Native Continuation for Action Chunking Flow Policies","display_name":"Learning Native Continuation for Action Chunking Flow Policies","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129063177","doi":"https://doi.org/10.48550/arxiv.2602.12978"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.12978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12978","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.2602.12978","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121199990","display_name":"Yufeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Yufeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126104943","display_name":"Hang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Hang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106395938","display_name":"Juntu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Juntu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126150519","display_name":"Bocheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bocheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126143440","display_name":"Di Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126154065","display_name":"Mingzhu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingzhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759486","display_name":"Wenxuan Wu","orcid":"https://orcid.org/0000-0002-5692-6051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wenxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126086354","display_name":"Yingdong Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yingdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126104863","display_name":"Junyuan Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Junyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126087909","display_name":"Junliang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Junliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074839390","display_name":"D. Y. Wang","orcid":"https://orcid.org/0000-0001-8270-8448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dequan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126074795","display_name":"Yang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5121199990"],"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":0.545199990272522,"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":0.545199990272522,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06530000269412994,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05950000137090683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/continuation","display_name":"Continuation","score":0.621999979019165},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6151999831199646},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5371999740600586},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.520799994468689},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.487199991941452},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.45559999346733093},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.451200008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808000206947327},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5795000195503235},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.517300009727478},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.12978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12978","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.2602.12978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12978","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Action":[0,5],"chunking":[1],"enables":[2],"Vision":[3],"Language":[4],"(VLA)":[6],"models":[7],"to":[8,32,36,75,86,109,131],"run":[9],"in":[10,156],"real":[11],"time,":[12],"but":[13,29],"naive":[14],"chunked":[15],"execution":[16],"often":[17],"exhibits":[18],"discontinuities":[19],"at":[20],"chunk":[21],"boundaries.":[22],"Real-Time":[23],"Chunking":[24],"(RTC)":[25],"alleviates":[26],"this":[27],"issue":[28],"is":[30],"external":[31],"the":[33,73,82,89],"policy,":[34],"leading":[35,130],"spurious":[37,125],"multimodal":[38,126],"switching":[39,127],"and":[40,70,96,114,123,134,160],"trajectories":[41,122],"that":[42,88,143],"are":[43],"not":[44],"intrinsically":[45],"smooth.":[46],"We":[47],"propose":[48],"Legato,":[49],"a":[50,64],"training-time":[51],"continuation":[52],"method":[53],"for":[54],"action-chunked":[55],"flow-based":[56],"VLA":[57],"policies.":[58],"Specifically,":[59],"Legato":[60,80,101,119,144],"initializes":[61],"denoising":[62,90],"from":[63],"schedule-shaped":[65],"mixture":[66],"of":[67],"known":[68],"actions":[69],"noise,":[71],"exposing":[72],"model":[74],"partial":[76],"action":[77],"information.":[78],"Moreover,":[79],"reshapes":[81],"learned":[83],"flow":[84],"dynamics":[85],"ensure":[87],"process":[91],"remains":[92],"consistent":[93],"between":[94],"training":[95,108],"inference":[97,112],"under":[98],"per-step":[99],"guidance.":[100],"further":[102],"uses":[103],"randomized":[104],"schedule":[105],"condition":[106],"during":[107,128],"support":[110],"varying":[111],"delays":[113],"achieve":[115],"controllable":[116],"smoothness.":[117],"Empirically,":[118],"produces":[120],"smoother":[121],"reduces":[124],"execution,":[129],"less":[132],"hesitation":[133],"shorter":[135],"task":[136,161],"completion":[137,162],"time.":[138,163],"Extensive":[139],"real-world":[140],"experiments":[141],"show":[142],"consistently":[145],"outperforms":[146],"RTC":[147],"across":[148],"five":[149],"manipulation":[150],"tasks,":[151],"achieving":[152],"approximately":[153],"10%":[154],"improvements":[155],"both":[157],"trajectory":[158],"smoothness":[159]},"counts_by_year":[],"updated_date":"2026-02-17T06:10:05.244387","created_date":"2026-02-17T00:00:00"}