{"id":"https://openalex.org/W7140204424","doi":"https://doi.org/10.48550/arxiv.2603.20658","title":"Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation","display_name":"Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140204424","doi":"https://doi.org/10.48550/arxiv.2603.20658"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20658","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.2603.20658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wu, Zhichao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Zhichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ye, Junyin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Junyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zhilong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Yihao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Haoxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Haoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luo, Jiaheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jiaheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ren, Haoxiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Haoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan, Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yu, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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":0.34929999709129333,"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":0.34929999709129333,"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":0.15809999406337738,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.06129999831318855,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.909500002861023},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6912000179290771},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5776000022888184},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5450999736785889},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.462799996137619},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4399999976158142},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.382099986076355}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.909500002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273000121116638},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5450999736785889},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3801000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20658","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.2603.20658","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20658","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":0.7410610914230347,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"current":[1],"embodied":[2,72],"policies":[3,73,168],"exhibit":[4],"remarkable":[5],"manipulation":[6],"skills,":[7],"their":[8,34,171],"execution":[9,164],"remains":[10],"unsatisfactorily":[11],"slow":[12],"as":[13,85,116,130],"they":[14],"inherit":[15],"the":[16,80,138],"tardy":[17],"pacing":[18],"of":[19,82],"human":[20],"demonstrations.":[21],"Existing":[22],"acceleration":[23,55],"methods":[24],"typically":[25],"require":[26],"policy":[27],"retraining":[28],"or":[29],"costly":[30],"online":[31],"interactions,":[32],"limiting":[33],"scalability":[35],"for":[36,166],"large-scale":[37],"foundation":[38],"models.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,78],"propose":[44],"Speedup":[45],"Patch":[46],"(SuP),":[47],"a":[48,86,117,126,131],"lightweight,":[49],"policy-agnostic":[50],"framework":[51],"that":[52,65,158],"enables":[53],"plug-and-play":[54],"using":[56],"solely":[57],"offline":[58,107,144],"data.":[59],"SuP":[60,109,159],"introduces":[61,110],"an":[62,161],"external":[63],"scheduler":[64,84,139],"adaptively":[66],"downsamples":[67],"action":[68],"chunks":[69],"provided":[70],"by":[71],"to":[74,120,134],"eliminate":[75],"redundancies.":[76],"Specifically,":[77],"formalize":[79],"optimization":[81],"our":[83],"Constrained":[87],"Markov":[88],"Decision":[89],"Process":[90],"(CMDP)":[91],"aimed":[92],"at":[93],"maximizing":[94],"efficiency":[95],"without":[96],"compromising":[97],"task":[98],"performance.":[99],"Since":[100],"direct":[101],"success":[102,173],"evaluation":[103],"is":[104],"infeasible":[105],"in":[106],"settings,":[108],"World":[111],"Model":[112],"based":[113],"state":[114],"deviation":[115],"surrogate":[118],"metric":[119],"enforce":[121],"safety":[122],"constraints.":[123],"By":[124],"leveraging":[125],"learned":[127],"world":[128],"model":[129],"virtual":[132],"evaluator":[133],"predict":[135],"counterfactual":[136],"trajectories,":[137],"can":[140],"be":[141],"optimized":[142],"via":[143],"reinforcement":[145],"learning.":[146],"Empirical":[147],"results":[148],"on":[149],"simulation":[150],"benchmarks":[151],"(Libero,":[152],"Bigym)":[153],"and":[154],"real-world":[155],"tasks":[156],"validate":[157],"achieves":[160],"overall":[162],"1.8x":[163],"speedup":[165],"diverse":[167],"while":[169],"maintaining":[170],"original":[172],"rates.":[174]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}