{"id":"https://openalex.org/W7128481096","doi":"https://doi.org/10.48550/arxiv.2602.08245","title":"STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction","display_name":"STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128481096","doi":"https://doi.org/10.48550/arxiv.2602.08245"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.08245","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059558695","display_name":"Jinhao Li","orcid":"https://orcid.org/0000-0001-6297-6285"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Jinhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125548285","display_name":"Yuxuan Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong, Yuxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125533896","display_name":"Yingqiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yingqiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125497531","display_name":"Hao Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125579209","display_name":"Shan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yijia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yijia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125502594","display_name":"Ningyi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ningyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125557777","display_name":"Guohao Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Guohao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5059558695"],"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/T10653","display_name":"Robot Manipulation and Learning","score":0.41510000824928284,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.41510000824928284,"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/T10982","display_name":"Motor Control and Adaptation","score":0.20329999923706055,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.09690000116825104,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/inference","display_name":"Inference","score":0.6093999743461609},{"id":"https://openalex.org/keywords/indirect-inference","display_name":"Indirect Inference","score":0.40059998631477356},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.32899999618530273},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.3230000138282776},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6093999743461609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43459999561309814},{"id":"https://openalex.org/C2779793024","wikidata":"https://www.wikidata.org/wiki/Q17299941","display_name":"Indirect Inference","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36719998717308044},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.08245","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.08245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08245","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":"pmh:doi:10.48550/arxiv.2602.08245","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":{"Diffusion":[0],"policies":[1],"have":[2],"recently":[3],"emerged":[4],"as":[5],"a":[6,79,115,141,150],"powerful":[7],"paradigm":[8],"for":[9,135],"visuomotor":[10],"control":[11,38],"in":[12,40],"robotic":[13],"manipulation":[14],"due":[15],"to":[16,19,33,63,85,95,130],"their":[17],"ability":[18],"model":[20],"the":[21,96,104,108,146,194,208],"distribution":[22],"of":[23,107,156,211],"action":[24,66,98,128,157],"sequences":[25],"and":[26,68,99,170,184,191,197,214],"capture":[27],"multimodality.":[28],"However,":[29],"iterative":[30],"denoising":[31],"leads":[32],"substantial":[34],"inference":[35,212],"latency,":[36],"limiting":[37],"frequency":[39],"real-time":[41],"closed-loop":[42],"systems.":[43],"Existing":[44],"acceleration":[45],"methods":[46],"either":[47],"reduce":[48],"sampling":[49],"steps,":[50],"bypass":[51],"diffusion":[52,110,160],"through":[53],"direct":[54],"prediction,":[55],"or":[56],"reuse":[57],"past":[58],"actions,":[59],"but":[60],"often":[61],"struggle":[62],"jointly":[64],"preserve":[65],"quality":[67],"achieve":[69,180],"consistently":[70,206],"low":[71],"latency.":[72],"In":[73],"this":[74],"work,":[75],"we":[76,113],"propose":[77,114],"STEP,":[78],"lightweight":[80],"spatiotemporal":[81],"consistency":[82],"prediction":[83,148],"mechanism":[84,119],"construct":[86],"high-quality":[87],"warm-start":[88],"actions":[89],"that":[90,120,145,204],"are":[91],"both":[92],"distributionally":[93],"close":[94],"target":[97],"temporally":[100],"consistent,":[101],"without":[102],"compromising":[103],"generative":[105],"capability":[106],"original":[109],"policy.":[111],"Then,":[112],"velocity-aware":[116],"perturbation":[117],"injection":[118],"adaptively":[121],"modulates":[122],"actuation":[123],"excitation":[124],"based":[125],"on":[126,166,193],"temporal":[127],"variation":[129],"prevent":[131],"execution":[132],"stall":[133],"especially":[134],"real-world":[136,172,198],"tasks.":[137,173],"We":[138,162],"further":[139],"provide":[140],"theoretical":[142],"analysis":[143],"showing":[144],"proposed":[147],"induces":[149],"locally":[151],"contractive":[152],"mapping,":[153],"ensuring":[154],"convergence":[155],"errors":[158],"during":[159],"refinement.":[161],"conduct":[163],"extensive":[164],"evaluations":[165],"nine":[167],"simulated":[168],"benchmarks":[169],"two":[171],"Notably,":[174],"STEP":[175,205],"with":[176],"2":[177],"steps":[178],"can":[179],"an":[181],"average":[182],"21.6%":[183],"27.5%":[185],"higher":[186],"success":[187,215],"rate":[188,216],"than":[189],"BRIDGER":[190],"DDIM":[192],"RoboMimic":[195],"benchmark":[196],"tasks,":[199],"respectively.":[200],"These":[201],"results":[202],"demonstrate":[203],"advances":[207],"Pareto":[209],"frontier":[210],"latency":[213],"over":[217],"existing":[218],"methods.":[219]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-11T00:00:00"}