{"id":"https://openalex.org/W7138256601","doi":"https://doi.org/10.1609/aaai.v40i12.37962","title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","display_name":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138256601","doi":"https://doi.org/10.1609/aaai.v40i12.37962"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37962","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37962","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37962/41924","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37962/41924","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115695140","display_name":"Mengchao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mengchao Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730895","display_name":"Wang Qiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang Qiang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697254","display_name":"Fan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Jiang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129717408","display_name":"Mu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Xu","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115695140"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60597015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"9966","last_page":"9974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.4803999960422516,"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/T11448","display_name":"Face recognition and analysis","score":0.4803999960422516,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.31349998712539673,"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/T10860","display_name":"Speech and Audio Processing","score":0.09489999711513519,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/preference","display_name":"Preference","score":0.7103000283241272},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.64410001039505},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3630000054836273},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3571999967098236},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3398999869823456},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.33980000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324000000953674},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7103000283241272},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6295999884605408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37962","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37962","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37962/41924","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37962","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37962","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37962/41924","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138256601.pdf","grobid_xml":"https://content.openalex.org/works/W7138256601.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,158,172,183],"audio-driven":[3],"portrait":[4,117],"animation":[5,118],"have":[6],"demonstrated":[7],"impressive":[8],"capabilities.":[9],"However,":[10],"existing":[11,156],"methods":[12,157],"struggle":[13],"to":[14,35,77],"align":[15],"with":[16,47,57,120,160],"fine-grained":[17,142],"human":[18,95,161],"preferences":[19,126],"across":[20,135,144],"multiple":[21],"dimensions,":[22],"such":[23],"as":[24],"motion":[25,175],"naturalness,":[26,176],"lip-sync":[27,173],"accuracy,":[28,174],"and":[29,50,137,177,186],"visual":[30,178],"quality.":[31],"This":[32],"is":[33],"due":[34],"the":[36,51],"difficulty":[37],"of":[38,53],"optimizing":[39],"among":[40],"competing":[41],"preference":[42,59,96,100,162],"objectives,":[43],"which":[44,131],"often":[45],"conflict":[46],"one":[48],"another,":[49],"scarcity":[52],"large-scale,":[54],"high-quality":[55],"datasets":[56],"multidimensional":[58,84,94,122],"annotations.":[60],"To":[61],"address":[62],"these,":[63],"we":[64,89,103],"first":[65],"introduce":[66],"Talking-Critic,":[67],"a":[68,92,111],"multimodal":[69],"reward":[70,75],"model":[71],"that":[72,152],"learns":[73],"human-aligned":[74],"functions":[76],"quantify":[78],"how":[79],"well":[80],"generated":[81],"videos":[82],"satisfy":[83],"expectations.":[85],"Leveraging":[86],"this":[87],"model,":[88],"curate":[90],"Talking-NSQ,":[91],"large-scale":[93],"dataset":[97],"containing":[98],"410K":[99],"pairs.":[101],"Finally,":[102],"propose":[104],"Timestep-Layer":[105],"adaptive":[106],"multi-expert":[107],"Preference":[108],"Optimization":[109],"(TLPO),":[110],"novel":[112],"framework":[113],"for":[114],"aligning":[115,159],"diffusion-based":[116],"models":[119,171],"fine-grained,":[121],"preferences.":[123],"TLPO":[124,165],"decouples":[125],"into":[127],"specialized":[128],"expert":[129],"modules,":[130],"are":[132],"then":[133],"fused":[134],"timesteps":[136],"network":[138],"layers,":[139],"enabling":[140],"comprehensive,":[141],"enhancement":[143],"all":[145],"dimensions":[146],"without":[147],"mutual":[148],"interference.":[149],"Experiments":[150],"demonstrate":[151],"Talking-Critic":[153],"significantly":[154],"outperforms":[155],"ratings.":[163],"Meanwhile,":[164],"achieves":[166],"substantial":[167],"improvements":[168],"over":[169],"baseline":[170],"quality,":[179],"exhibiting":[180],"superior":[181],"performance":[182],"both":[184],"qualitative":[185],"quantitative":[187],"evaluations.":[188]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}