{"id":"https://openalex.org/W7138398834","doi":"https://doi.org/10.1609/aaai.v40i10.37725","title":"Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback","display_name":"Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138398834","doi":"https://doi.org/10.1609/aaai.v40i10.37725"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37725","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37725","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.v40i10.37725","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121597287","display_name":"Xingpei Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingpei Ma","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742965","display_name":"Shenneng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenneng Huang","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002400996","display_name":"Jiaran Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaran Cai","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020584403","display_name":"Yuansheng Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuansheng Guan","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129675135","display_name":"Shen Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Zheng","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101492535","display_name":"Haiyun Zhao","orcid":"https://orcid.org/0000-0002-8920-9016"},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanfeng Zhao","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662465","display_name":"Qiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111110986","display_name":"Shunsi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunsi Zhang","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co. Limited Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co. Limited Ltd,","institution_ids":["https://openalex.org/I4210150595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150595"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27444851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7818","last_page":"7826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3734999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3734999895095825,"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/T12290","display_name":"Human Motion and Animation","score":0.32510000467300415,"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/T11448","display_name":"Face recognition and analysis","score":0.11240000277757645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5625},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42500001192092896},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4018000066280365},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4002000093460083},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3188000023365021},{"id":"https://openalex.org/keywords/video-streaming","display_name":"Video streaming","score":0.30559998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188999891281128},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180000066757202},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.43970000743865967},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4002000093460083},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37725","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37725","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/37725","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37725","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.v40i10.37725","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37725","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,15,26,160],"diffusion":[3,44],"models":[4],"have":[5],"significantly":[6],"improved":[7],"audio-driven":[8,63,134,157],"human":[9],"video":[10,33,83,158],"generation,":[11,34],"surpassing":[12],"traditional":[13],"methods":[14],"both":[16,104],"quality":[17],"and":[18,35,56,107,132,155,164],"controllability.":[19],"However,":[20],"existing":[21,148],"approaches":[22],"still":[23],"face":[24],"challenges":[25],"lip-sync":[27],"accuracy,":[28],"temporal":[29],"coherence":[30],"for":[31,48,61,121,136],"long":[32,82],"multi-character":[36,62,122,156],"animation.":[37,64],"In":[38],"this":[39],"work,":[40],"we":[41,66,94,112],"propose":[42,113],"a":[43,58,68,74,114,161],"transformer":[45],"(DiT)-based":[46],"framework":[47],"generating":[49],"lifelike":[50],"talking":[51],"videos":[52],"of":[53,89],"arbitrary":[54],"length,":[55],"introduce":[57],"training-free":[59,115],"method":[60,146],"First,":[65],"employ":[67],"LoRA-based":[69],"training":[70],"strategy":[71],"combined":[72],"with":[73,99],"position":[75],"shift":[76],"inference":[77],"approach,":[78,116],"which":[79,124],"enables":[80],"efficient":[81],"generation":[84,159],"while":[85],"preserving":[86],"the":[87,90],"capabilities":[88],"foundation":[91],"model.":[92],"Moreover,":[93],"combine":[95],"partial":[96],"parameter":[97],"updates":[98],"reward":[100],"feedback":[101],"to":[102],"enhance":[103],"lip":[105],"synchronization":[106],"natural":[108],"body":[109],"motion.":[110],"Finally,":[111],"Mask":[117],"Classifier-Free":[118],"Guidance":[119],"(Mask-CFG),":[120],"animation,":[123],"requires":[125],"no":[126],"specialized":[127],"datasets":[128],"or":[129,138],"model":[130],"modifications":[131],"supports":[133],"animation":[135],"three":[137],"more":[139],"characters.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"that":[144],"our":[145],"outperforms":[147],"state-of-the-art":[149],"approaches,":[150],"achieving":[151],"high-quality,":[152],"temporally":[153],"coherent,":[154],"simple,":[162],"efficient,":[163],"cost-effective":[165],"manner.":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}
