{"id":"https://openalex.org/W7213610374","doi":"https://doi.org/10.48550/arxiv.2609.20761","title":"Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control","display_name":"Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213610374","doi":"https://doi.org/10.48550/arxiv.2609.20761"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.20761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20761","pdf_url":"https://arxiv.org/pdf/2609.20761","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/2609.20761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042064864","display_name":"Hanchu Zhou","orcid":"https://orcid.org/0000-0002-6305-7907","observed_orcids":["https://orcid.org/0000-0002-6305-7907","https://orcid.org/0009-0002-6712-705X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hanchu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152130240","display_name":"Brendan Lynch","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynch, Brendan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072338368","display_name":"Raman Goyal","orcid":"https://orcid.org/0000-0002-8128-3051","observed_orcids":["https://orcid.org/0000-0002-8128-3051"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goyal, Raman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018828704","display_name":"Dechen Gao","orcid":"https://orcid.org/0009-0006-4434-5731","observed_orcids":["https://orcid.org/0009-0006-4434-5731","https://orcid.org/0000-0001-5131-0744"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Dechen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076266329","display_name":"Begum Kasap","orcid":"https://orcid.org/0000-0001-5894-2883","observed_orcids":["https://orcid.org/0000-0001-5894-2883"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kasap, Begum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152137350","display_name":"Boqi Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Boqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5152151355","display_name":"Junshan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Junshan","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":0.9164999723434448,"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":0.9164999723434448,"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":0.0812000036239624,"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/T10982","display_name":"Motor Control and Adaptation","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/world-action-models","display_name":"world action models","score":0.9309999942779541},{"id":"https://openalex.org/keywords/tactile-sensing","display_name":"tactile sensing","score":0.8709999918937683},{"id":"https://openalex.org/keywords/contact-rich-manipulation","display_name":"contact-rich manipulation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.7440000176429749},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.7829999923706055},{"id":"https://openalex.org/keywords/multi-horizon-prediction","display_name":"multi-horizon prediction","score":0.8539999723434448},{"id":"https://openalex.org/keywords/shared-latent-representation","display_name":"shared latent representation","score":0.5450000166893005},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5974000096321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5947999954223633},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C46722567","wikidata":"https://www.wikidata.org/wiki/Q7674139","display_name":"Tactile sensor","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2644999921321869},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.20761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20761","pdf_url":"https://arxiv.org/pdf/2609.20761","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.2609.20761","doi":"https://doi.org/10.48550/arxiv.2609.20761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20761","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.20761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20761","pdf_url":"https://arxiv.org/pdf/2609.20761","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7172172563","https://openalex.org/W7167248979","https://openalex.org/W7166081644","https://openalex.org/W7215783801","https://openalex.org/W7171535589","https://openalex.org/W7203880014","https://openalex.org/W7164026271","https://openalex.org/W7214001523","https://openalex.org/W7214037125","https://openalex.org/W7160903845"],"abstract_inverted_index":{"World":[0,63],"Action":[1,64],"Models":[2],"(WAMs)":[3],"advance":[4],"beyond":[5],"conventional":[6],"visuomotor":[7],"policies":[8],"by":[9],"jointly":[10,93],"predicting":[11,153],"future":[12,101],"world":[13],"states":[14],"and":[15,51,73,100,110,169,179,234],"robot":[16,68,236],"actions,":[17],"enabling":[18],"the":[19,83,154,158,183],"policy":[20],"to":[21,41,161],"learn":[22],"phys-":[23],"ical":[24],"dynamics":[25],"that":[26,80,108,221],"support":[27],"effective":[28],"control.":[29,69,237],"However,":[30],"recent":[31],"tactile":[32,62,74,111,126,155],"WAMs":[33],"often":[34,122],"rely":[35],"on":[36,242],"large-scale":[37],"pretrained":[38],"generative":[39],"backbones":[40],"capture":[42,162],"contact-rich":[43,67,172],"physical":[44],"dynamics,":[45],"which":[46,91,141],"limit":[47],"their":[48],"inference":[49,192,213],"efficiency":[50],"flexible":[52],"deployment.":[53],"In":[54,194],"this":[55],"paper,":[56],"we":[57],"present":[58],"Agile-WAM,":[59,140],"an":[60,228],"agile":[61,229],"Model":[65],"for":[66,144,232],"Agile-WAM":[70,176,200],"encodes":[71],"visual":[72,119,145],"observations":[75],"into":[76],"a":[77,86,148,202],"shared":[78],"latent":[79,95,146,156],"serves":[81],"as":[82],"source":[84],"of":[85,97,205,215],"direct":[87],"vision-tactile-to-action":[88],"flow-matching":[89],"process,":[90],"can":[92,128,224],"generate":[94],"representations":[96],"action":[98],"chunks":[99],"visual/tactile":[102],"latents.":[103],"A":[104],"key":[105],"observation":[106],"is":[107],"vision":[109],"signals":[112,127],"evolve":[113],"at":[114,147],"inherently":[115],"different":[116],"timescales:":[117],"adjacent":[118],"frames":[120],"are":[121,240],"highly":[123],"similar,":[124],"whereas":[125],"change":[129],"abruptly":[130],"upon":[131],"contact.":[132],"We":[133],"therefore":[134],"introduce":[135],"multi-horizon":[136],"multimodal":[137,222],"prediction":[138],"in":[139,157,186,196,207],"provides":[142],"supervision":[143],"larger":[149],"temporal":[150],"offset":[151],"while":[152,189,211],"next":[159],"frame":[160],"fine-grained":[163],"contact":[164],"dynamics.":[165],"Across":[166],"nine":[167],"simulated":[168],"five":[170,197],"real-world":[171,198],"ma-":[173],"nipulation":[174],"tasks,":[175],"demonstrates":[177],"strong":[178],"robust":[180],"performance,":[181],"outperforming":[182],"strongest":[184],"baseline":[185],"success":[187,209],"rate":[188],"maintaining":[190],"low":[191],"latency.":[193],"particular,":[195],"experiments,":[199],"yields":[201],"relative":[203],"gain":[204],"29.4%":[206],"overall":[208],"rates":[210],"achieving":[212],"latency":[214],"11.9":[216],"ms.":[217],"These":[218],"results":[219],"demonstrate":[220],"WAM":[223],"be":[225],"achieved":[226],"with":[227],"architecture":[230],"suitable":[231],"precise":[233],"high-frequency":[235],"More":[238],"details":[239],"available":[241],"our":[243],"project":[244],"page.":[245]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-19T00:00:00"}