{"id":"https://openalex.org/W7225189391","doi":"https://doi.org/10.48550/arxiv.2611.03394","title":"TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation","display_name":"TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225189391","doi":"https://doi.org/10.48550/arxiv.2611.03394"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03394","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03394","pdf_url":"https://arxiv.org/pdf/2611.03394","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058867239","display_name":"Qijun Gan","orcid":"https://orcid.org/0009-0007-9849-8060","observed_orcids":["https://orcid.org/0009-0007-9849-8060"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Qijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160430079","display_name":"Chenwei Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160435825","display_name":"Xinyang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046381970","display_name":"Meiguang Jin","orcid":"https://orcid.org/0000-0003-3796-2310","observed_orcids":["https://orcid.org/0000-0003-3796-2310"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Meiguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160395668","display_name":"Junfeng Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Junfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160396604","display_name":"Shen Qiu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Shen","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9589999914169312,"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":0.9589999914169312,"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":0.017500000074505806,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.01489999983459711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-generation","display_name":"autoregressive generation","score":0.6840000152587891},{"id":"https://openalex.org/keywords/high-resolution-video-generation","display_name":"high-resolution video generation","score":0.5699999928474426},{"id":"https://openalex.org/keywords/text-conditioning","display_name":"text conditioning","score":0.3179999887943268},{"id":"https://openalex.org/keywords/character-error-rate","display_name":"character error rate","score":0.7039999961853027},{"id":"https://openalex.org/keywords/virtual-humans","display_name":"virtual humans","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.8141999840736389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870000004768372},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7468000054359436},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7391999959945679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5198000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49320000410079956},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.27799999713897705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C74883015","wikidata":"https://www.wikidata.org/wiki/Q290467","display_name":"Autoregressive\u2013moving-average model","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03394","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03394","pdf_url":"https://arxiv.org/pdf/2611.03394","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.2611.03394","doi":"https://doi.org/10.48550/arxiv.2611.03394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03394","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03394","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03394","pdf_url":"https://arxiv.org/pdf/2611.03394","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/W7171543272","https://openalex.org/W4415135974","https://openalex.org/W7201840745","https://openalex.org/W7154737732","https://openalex.org/W7115573277","https://openalex.org/W7212824920","https://openalex.org/W7203633965","https://openalex.org/W7204235261","https://openalex.org/W7156847872","https://openalex.org/W7140213015"],"abstract_inverted_index":{"Streaming":[0],"digital":[1],"humans":[2],"produce":[3],"detailed":[4],"video":[5,47,57],"while":[6],"continuing":[7],"speech":[8],"as":[9,82],"new":[10],"text":[11,18,85,103,107],"arrives.":[12],"High-resolution":[13],"denoising":[14,43],"is":[15,166],"costly,":[16],"and":[17,111,126],"updates":[19],"can":[20],"cause":[21],"repeated":[22],"or":[23,40],"interrupted":[24],"speech.":[25],"We":[26],"present":[27],"TaoMate-HD,":[28],"an":[29],"autoregressive":[30],"model":[31,88,125,157],"for":[32,109],"high-resolution":[33,120],"audio-video":[34],"streaming.":[35],"For":[36],"each":[37],"short":[38],"segment,":[39],"chunk,":[41],"two":[42],"steps":[44],"establish":[45],"coarse":[46],"structure":[48],"at":[49],"low":[50],"resolution.":[51],"A":[52],"final":[53],"step":[54],"refines":[55],"the":[56,65,75,79,87,123,154],"to":[58,74,92,153],"high":[59],"resolution,":[60],"with":[61,105,122],"audio":[62],"generated":[63],"throughout":[64],"same":[66,76,124],"trajectory.":[67],"Each":[68],"stage":[69,77],"passes":[70],"its":[71],"audiovisual":[72,161],"predictions":[73],"of":[78],"next":[80],"chunk":[81],"history.":[83],"Across":[84],"updates,":[86],"retains":[89],"this":[90],"history":[91],"infer":[93],"what":[94],"has":[95],"already":[96],"been":[97],"spoken.":[98],"Continuation":[99],"training":[100,143],"utilizes":[101],"asymmetric":[102],"conditioning,":[104],"separate":[106],"windows":[108],"generation":[110,121],"distillation.":[112],"Experiments":[113],"show":[114],"a":[115,132],"1.6x":[116],"speedup":[117,136],"over":[118,137],"direct":[119],"hardware.":[127],"Optimized":[128],"stage-parallel":[129],"deployment":[130],"provides":[131],"further":[133],"1.9x":[134],"overall":[135],"serial":[138],"progressive":[139],"generation.":[140,162],"Our":[141,163],"continuation":[142],"reduces":[144],"character":[145],"error":[146],"rate":[147],"by":[148],"11.18":[149],"percentage":[150],"points":[151],"relative":[152],"baseline.":[155],"The":[156],"also":[158],"supports":[159],"hour-long":[160],"project":[164],"page":[165],"https://taoliveaigc.github.io/TaoMate-HD.":[167]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}