{"id":"https://openalex.org/W7138089267","doi":"https://doi.org/10.1609/aaai.v40i5.37402","title":"MOGO: Residual Quantized Hierarchical Causal Transformer for Real-Time and Infinite-Length 3D Human Motion Generation","display_name":"MOGO: Residual Quantized Hierarchical Causal Transformer for Real-Time and Infinite-Length 3D Human Motion Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138089267","doi":"https://doi.org/10.1609/aaai.v40i5.37402"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37402","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37402","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i5.37402","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101485171","display_name":"Dongjie Fu","orcid":"https://orcid.org/0009-0000-7682-7678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongjie Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129654395","display_name":"Tengjiao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tengjiao Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736393","display_name":"Pengcheng Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078326698","display_name":"Xiaohao Cai","orcid":"https://orcid.org/0000-0003-0924-2834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohao Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022128293","display_name":"Hansung Kim","orcid":"https://orcid.org/0000-0003-2506-7992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansung Kim","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3994","last_page":"4002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8634999990463257,"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":0.8634999990463257,"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":0.06729999929666519,"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":0.01940000057220459,"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/inference","display_name":"Inference","score":0.5662000179290771},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5130000114440918},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46309998631477356},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4230000078678131},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.38100001215934753},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3422999978065491},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.33059999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844000220298767},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4230000078678131},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37402","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37402","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37402","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37402","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37402","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1710977924","display_name":null,"funder_award_id":"24ZC1200","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,99,166,235],"transformer-based":[3],"text-to-motion":[4],"generation":[5,118,236],"have":[6],"significantly":[7],"improved":[8],"motion":[9,43,56,65,97,137,149,210],"quality.":[10],"However,":[11],"achieving":[12],"both":[13],"real-time":[14],"performance":[15,203],"and":[16,39,77,115,126,146,154,172,195,224,240],"long-horizon":[17],"scalability":[18],"remains":[19],"an":[20],"open":[21],"challenge.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,52,85,174],"present":[27],"MOGO":[28,45,129,231],"(Motion":[29],"Generation":[30],"with":[31,108,119,151,185],"One-pass),":[32],"a":[33,55,89,100],"novel":[34],"autoregressive":[35],"framework":[36],"for":[37,212],"efficient":[38],"scalable":[40],"3D":[41],"human":[42],"generation.":[44],"consists":[46],"of":[47,74],"two":[48],"key":[49],"components.":[50],"First,":[51],"introduce":[53,175],"MoSA-VQ,":[54],"scale-adaptive":[57],"residual":[58,90],"vector":[59],"quantization":[60,110],"module":[61],"that":[62,95,230],"hierarchically":[63],"discretizes":[64],"sequences":[66],"through":[67,215],"learnable":[68],"scaling":[69],"parameters,":[70],"enabling":[71],"dynamic":[72],"allocation":[73],"representation":[75],"capacity":[76],"producing":[78],"compact":[79],"yet":[80],"expressive":[81],"multi-level":[82],"representations.":[83],"Second,":[84],"design":[86,143],"the":[87,155,190,225],"RQHC-Transformer,":[88],"quantized":[91],"hierarchical":[92,113,141],"causal":[93],"transformer":[94,105],"decodes":[96],"tokens":[98],"single":[101],"forward":[102],"pass.":[103],"Each":[104],"block":[106],"aligns":[107],"one":[109],"level,":[111],"allowing":[112],"abstraction":[114],"temporally":[116],"coherent":[117],"strong":[120],"semantic":[121],"flow.":[122],"Compared":[123],"to":[124,157,188],"diffusion-":[125],"LLM-based":[127],"approaches,":[128],"achieves":[130],"lower":[131],"inference":[132,238],"latency":[133],"while":[134],"preserving":[135],"high":[136],"fidelity.":[138],"Moreover,":[139],"its":[140],"latent":[142],"enables":[144],"seamless":[145],"controllable":[147],"infinite-length":[148],"generation,":[150],"stable":[152],"transitions":[153],"ability":[156],"adaptively":[158],"incorporate":[159],"updated":[160],"control":[161],"signals":[162],"at":[163],"arbitrary":[164],"points":[165],"time.":[167],"To":[168],"further":[169],"enhance":[170],"generalization":[171],"interpretability,":[173],"Textual":[176],"Condition":[177],"Alignment":[178],"(TCA),":[179],"which":[180],"leverages":[181],"large":[182],"language":[183],"models":[184],"Chain-of-Thought":[186],"reasoning":[187],"bridge":[189],"gap":[191],"between":[192],"real-world":[193],"prompts":[194,214],"training":[196],"data.":[197],"TCA":[198],"not":[199],"only":[200],"improves":[201],"zero-shot":[202],"on":[204,221],"unseen":[205,226],"datasets":[206],"but":[207],"also":[208],"enriches":[209],"comprehension":[211],"in-distribution":[213],"explicit":[216],"intent":[217],"decomposition.":[218],"Extensive":[219],"experiments":[220],"HumanML3D,":[222],"KIT-ML,":[223],"CMP":[227],"dataset":[228],"demonstrate":[229],"outperforms":[232],"prior":[233],"methods":[234],"quality,":[237],"efficiency,":[239],"temporal":[241],"scalability.":[242]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}