{"id":"https://openalex.org/W7167251437","doi":"https://doi.org/10.1145/3811284","title":"Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","display_name":"Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W7167251437","doi":"https://doi.org/10.1145/3811284"},"language":"en","primary_location":{"id":"doi:10.1145/3811284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811284","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3811284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101516591","display_name":"Kaifeng Zhao","orcid":"https://orcid.org/0000-0002-7278-3329"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kaifeng Zhao","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland","NVIDIA, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7278-3329","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"NVIDIA, Zurich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091623941","display_name":"Mathis Petrovich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathis Petrovich","raw_affiliation_strings":["NVIDIA, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0859-1170","affiliations":[{"raw_affiliation_string":"NVIDIA, Zurich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392974","display_name":"Haotian Zhang","orcid":"https://orcid.org/0009-0008-0293-337X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Zhang","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0009-0008-0293-337X","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091475385","display_name":"Tingwu Wang","orcid":"https://orcid.org/0000-0003-2006-0660"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingwu Wang","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-2006-0660","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056265728","display_name":"Siyu Tang","orcid":"https://orcid.org/0000-0002-1015-4770"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Siyu Tang","raw_affiliation_strings":["ETH Z\u00fcrich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1015-4770","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078529189","display_name":"Davis Rempe","orcid":"https://orcid.org/0000-0003-2256-5507"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davis Rempe","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-2256-5507","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87857268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"4","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9271000027656555,"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/T12290","display_name":"Human Motion and Animation","score":0.9271000027656555,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02199999988079071,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.00989999994635582,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/kinematics","display_name":"Kinematics","score":0.6696000099182129},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.598800003528595},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.44020000100135803},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4390999972820282},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4300999939441681},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.38749998807907104},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012999892234802},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.598800003528595},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715999960899353},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4345000088214874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.38749998807907104},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3811284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811284","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2607.08741","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.08741","pdf_url":"https://arxiv.org/pdf/2607.08741","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3811284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811284","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1735317348","https://openalex.org/W2611706523","https://openalex.org/W2949924544","https://openalex.org/W2986708244","https://openalex.org/W3048550213","https://openalex.org/W4214677627","https://openalex.org/W4214679856","https://openalex.org/W4229044820","https://openalex.org/W4286611302","https://openalex.org/W4288079574","https://openalex.org/W4297981470","https://openalex.org/W4312495732","https://openalex.org/W4312635677","https://openalex.org/W4386065848","https://openalex.org/W4386066131","https://openalex.org/W4387963302","https://openalex.org/W4390871696","https://openalex.org/W4390874263","https://openalex.org/W4400573489","https://openalex.org/W4400581049","https://openalex.org/W4402716444","https://openalex.org/W4402727037","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4402916263","https://openalex.org/W4404966227","https://openalex.org/W4412673622","https://openalex.org/W4413146746","https://openalex.org/W4413147141","https://openalex.org/W4413513955","https://openalex.org/W7160087114","https://openalex.org/W7160105287","https://openalex.org/W7160157512"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"realistic":[1],"3D":[2],"human":[3],"motions":[4],"in":[5],"real-time":[6,46],"within":[7],"interactive":[8,39,211,224],"applications":[9],"is":[10],"key":[11,199],"for":[12,38],"animation,":[13],"simulation,":[14],"and":[15,29,58,90,129,145,152,169,179,191,223,229,235],"humanoid":[16],"robotics.":[17],"While":[18],"recent":[19],"offline":[20],"motion":[21,83,142,189],"generation":[22,74,84,164],"approaches":[23],"offer":[24],"precise":[25,110],"control":[26,112,226],"via":[27,86,227],"text":[28,56,88,150,215],"kinematic":[30,92,135,153],"constraints,":[31,220],"they":[32],"lack":[33],"the":[34,176,180,195,205],"inference":[35],"speed":[36],"required":[37],"settings.":[40],"Conversely,":[41],"existing":[42],"online":[43,87,167],"methods":[44],"enable":[45],"synthesis":[47],"but":[48],"often":[49],"sacrifice":[50],"controllability":[51],"or":[52],"struggle":[53],"with":[54,104,113],"complex":[55],"semantics":[57],"long-horizon":[59,134,171],"goals":[60],"due":[61],"to":[62],"limited":[63],"context":[64,128],"windows.":[65],"In":[66],"this":[67,78],"work,":[68],"we":[69,203],"introduce":[70],"ARDY,":[71],"a":[72,96,105,119,140],"streaming":[73],"framework":[75],"that":[76,99,124,165],"bridges":[77],"gap":[79],"by":[80],"enabling":[81],"high-fidelity":[82,182],"controllable":[85,163],"prompts":[89],"flexible":[91,170],"constraints.":[93,136],"ARDY":[94,160],"employs":[95],"hybrid":[97],"representation":[98],"combines":[100],"explicit":[101],"root":[102],"features":[103,125],"latent":[106],"body":[107],"embedding,":[108],"balancing":[109],"trajectory":[111],"efficient":[114],"generative":[115],"learning.":[116],"We":[117],"propose":[118],"two-stage":[120],"autoregressive":[121],"transformer":[122],"denoiser":[123],"variable":[126],"history":[127],"supports":[130,166],"conditioning":[131],"on":[132,139,149,175],"flexible,":[133],"By":[137],"training":[138],"large-scale":[141],"capture":[143],"dataset":[144,185],"being":[146],"directly":[147],"conditioned":[148],"labels":[151],"constraints":[154],"sampled":[155],"from":[156],"ground":[157],"truth":[158],"poses,":[159],"natively":[161],"learns":[162],"prompting":[168],"goals.":[172],"Extensive":[173],"evaluations":[174],"HumanML3D":[177],"benchmark":[178],"large-scale,":[181],"Bones":[183],"Rigplay":[184],"demonstrate":[186,204],"ARDY's":[187],"high":[188],"quality":[190],"constraint":[192],"adherence,":[193],"validating":[194],"efficacy":[196],"of":[197],"our":[198],"architectural":[200],"decisions.":[201],"Finally,":[202],"method's":[206],"practical":[207],"versatility":[208],"through":[209],"an":[210],"demo":[212],"featuring":[213],"dynamic":[214],"control,":[216],"diverse":[217],"keyframe":[218],"pose":[219],"path":[221],"following,":[222],"locomotion":[225],"mouse":[228],"keyboard.":[230],"Supplementary":[231],"video":[232],"results,":[233],"code,":[234],"model":[236],"releases":[237],"can":[238],"be":[239],"found":[240],"at":[241],"https://research.nvidia.com/labs/sil/projects/ardy/.":[242]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2026-07-04T00:00:00"}