{"id":"https://openalex.org/W7225180290","doi":"https://doi.org/10.48550/arxiv.2611.02600","title":"W2A: Distilling World Priors into Action Models for Real-Time Robotic Control","display_name":"W2A: Distilling World Priors into Action Models for Real-Time Robotic Control","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225180290","doi":"https://doi.org/10.48550/arxiv.2611.02600"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02600","pdf_url":"https://arxiv.org/pdf/2611.02600","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02600","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160435958","display_name":"Xiaopeng Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085521136","display_name":"Yongjin Mu","orcid":"https://orcid.org/0009-0008-3147-8644","observed_orcids":["https://orcid.org/0009-0008-3147-8644"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Yongjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056733401","display_name":"Yueyang Weng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Yueyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159035633","display_name":"Chengzhi Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chengzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160546689","display_name":"Yanjie Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yanjie","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/T10653","display_name":"Robot Manipulation and Learning","score":0.9115999937057495,"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":0.9115999937057495,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07890000194311142,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.003000000026077032,"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/world-action-models","display_name":"world action models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.7490000128746033},{"id":"https://openalex.org/keywords/video-diffusion-models","display_name":"video diffusion models","score":0.7950000166893005},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.9509999752044678},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.7170000076293945},{"id":"https://openalex.org/keywords/libero-benchmark","display_name":"LIBERO benchmark","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013999819755554},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6514999866485596},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5030999779701233},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3946000039577484},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02600","pdf_url":"https://arxiv.org/pdf/2611.02600","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02600","doi":"https://doi.org/10.48550/arxiv.2611.02600","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02600","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02600","pdf_url":"https://arxiv.org/pdf/2611.02600","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164153965","https://openalex.org/W7172380766","https://openalex.org/W7164040202","https://openalex.org/W7204206613","https://openalex.org/W7163686620","https://openalex.org/W7223125825","https://openalex.org/W7220972405","https://openalex.org/W7196977530","https://openalex.org/W7214331945","https://openalex.org/W7223019149"],"abstract_inverted_index":{"World":[0],"Action":[1],"Models":[2],"(WAMs)":[3],"have":[4],"recently":[5],"shown":[6],"great":[7],"promise":[8],"in":[9,125],"robotic":[10,47,61],"control,":[11],"benefiting":[12],"from":[13,68],"the":[14,82,158],"future":[15,30],"imagination":[16],"capability":[17],"of":[18],"large-scale":[19],"pretrained":[20],"video":[21,70,83,92],"models.":[22],"However,":[23],"most":[24],"existing":[25],"WAMs":[26],"require":[27],"explicitly":[28],"imagining":[29],"states":[31],"at":[32,85],"test":[33,86],"time,":[34],"incurring":[35],"substantial":[36],"computational":[37],"overhead":[38],"and":[39,128],"latency":[40],"that":[41,63,90],"make":[42],"them":[43],"unsuitable":[44],"for":[45,59,107],"real-time":[46,60],"control.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"W2A,":[54],"a":[55,69,97,144],"two-stage":[56],"distillation":[57],"framework":[58],"manipulation":[62],"distills":[64],"intermediate":[65],"denoising":[66],"representations":[67,94],"diffusion":[71],"model":[72,76,84],"into":[73,119],"an":[74,120],"action":[75,108,121],"during":[77],"training,":[78],"while":[79,135],"entirely":[80],"discarding":[81],"time.":[87],"We":[88],"hypothesize":[89],"although":[91],"latent":[93],"are":[95],"high-dimensional,":[96],"compressed":[98],"low-dimensional":[99],"subspace":[100],"is":[101],"sufficient":[102],"to":[103,114],"provide":[104],"effective":[105],"supervision":[106],"generation.":[109],"This":[110],"makes":[111],"it":[112],"possible":[113],"transfer":[115],"such":[116],"information":[117],"effectively":[118],"model.":[122],"Extensive":[123],"experiments":[124],"both":[126],"simulation":[127],"real-world":[129],"settings":[130],"demonstrate":[131],"competitive":[132],"success":[133,147],"rates":[134],"significantly":[136],"improving":[137],"inference":[138,156],"efficiency.":[139],"On":[140],"LIBERO,":[141],"W2A":[142,151],"achieves":[143,152],"95.9%":[145],"average":[146],"rate.":[148],"More":[149],"importantly,":[150],"about":[153],"21x":[154],"faster":[155],"than":[157],"representative":[159],"WAM":[160],"baseline.":[161]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}