{"id":"https://openalex.org/W7133298179","doi":"https://doi.org/10.48550/arxiv.2603.01581","title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","display_name":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133298179","doi":"https://doi.org/10.48550/arxiv.2603.01581"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01581","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.2603.01581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127943427","display_name":"Zihao Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng, Zihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127932994","display_name":"Zhihao Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Zhihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127931013","display_name":"Maoliang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Maoliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127936945","display_name":"Jiayu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiayu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128013116","display_name":"Xinhao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xinhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127941642","display_name":"Zhaobo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhaobo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127879585","display_name":"Donggang Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Donggang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633784","display_name":"Hong Mei","orcid":"https://orcid.org/0000-0003-2380-3976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Hong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127956961","display_name":"Xiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5127943427"],"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.35249999165534973,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.35249999165534973,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12389999628067017,"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":0.07339999824762344,"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/decoding-methods","display_name":"Decoding methods","score":0.6689000129699707},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6477000117301941},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5945000052452087},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5695000290870667},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.508400022983551},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4187000095844269},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401999831199646},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6689000129699707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01581","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.2603.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01581","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":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,100],"build":[3],"a":[4,107,115,133],"token-domain":[5,98],"robot":[6],"control":[7],"paradigm,":[8],"yet":[9],"suffer":[10],"from":[11],"low":[12],"speed.":[13,25],"Speculative":[14],"Decoding":[15],"(SD)":[16],"is":[17,45],"an":[18],"optimization":[19],"strategy":[20,136],"that":[21,157],"can":[22],"boost":[23],"inference":[24],"Two":[26],"key":[27],"issues":[28,69],"emerge":[29],"when":[30],"integrating":[31],"VLA":[32,99],"and":[33,77,122,154],"SD:":[34],"first,":[35],"SD":[36,57,109,125],"relies":[37],"on":[38],"re-inference":[39],"to":[40,49,64,119,137],"address":[41,65,92],"token":[42,51],"errors,":[43,52,126],"which":[44],"computationally":[46],"expensive;":[47],"second,":[48],"mitigate":[50],"the":[53,66,73,78,86,140,144],"acceptance":[54,141],"threshold":[55,147],"in":[56],"requires":[58],"careful":[59],"adjustment.":[60],"Existing":[61],"works":[62],"fail":[63],"above":[67],"two":[68],"effectively.":[70],"Meanwhile,":[71],"as":[72],"bridge":[74],"between":[75],"AI":[76],"physical":[79],"world,":[80],"existing":[81],"embodied":[82],"intelligence":[83],"has":[84],"overlooked":[85],"application":[87],"of":[88,146],"robotic":[89],"kinematics.":[90],"To":[91],"these":[93],"issues,":[94],"we":[95,131],"innovatively":[96],"combine":[97],"with":[101,162],"kinematic-domain":[102],"prediction":[103],"for":[104,124],"SD,":[105],"proposing":[106],"kinematic-rectified":[108],"framework":[110],"named":[111],"KERV.":[112],"We":[113],"employ":[114],"kinematics-based":[116,134],"Kalman":[117],"Filter":[118],"predict":[120],"actions":[121],"compensate":[123],"avoiding":[127],"costly":[128],"re-inference.":[129],"Moreover,":[130],"design":[132],"adjustment":[135],"dynamically":[138],"rectify":[139],"threshold,":[142],"addressing":[143],"difficulty":[145],"determination.":[148],"Experimental":[149],"results":[150],"across":[151],"diverse":[152],"tasks":[153],"environments":[155],"demonstrate":[156],"KERV":[158],"achieves":[159],"27%~37%":[160],"acceleration":[161],"nearly":[163],"no":[164],"Success":[165],"Rate":[166],"loss.":[167]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}