{"id":"https://openalex.org/W7225834931","doi":"https://doi.org/10.48550/arxiv.2611.14307","title":"TaoMate-R1: Temporal Role Specialization for Streaming Multi-Reference Video Generation","display_name":"TaoMate-R1: Temporal Role Specialization for Streaming Multi-Reference Video Generation","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225834931","doi":"https://doi.org/10.48550/arxiv.2611.14307"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.14307","doi":"https://doi.org/10.48550/arxiv.2611.14307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.14307","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.14307","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/A5161432232","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/A5161429517","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":"last","author":{"id":"https://openalex.org/A5161444237","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":[]}],"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813000082969666},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.39820000529289246},{"id":"https://openalex.org/C73313986","wikidata":"https://www.wikidata.org/wiki/Q355386","display_name":"Luminance","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.14307","doi":"https://doi.org/10.48550/arxiv.2611.14307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.14307","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":"doi:10.48550/arxiv.2611.14307","doi":"https://doi.org/10.48550/arxiv.2611.14307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.14307","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Streaming":[0],"multi-reference":[1,23,101,172],"video":[2],"generation":[3],"establishes":[4],"a":[5,21,44],"scene":[6,39,166],"from":[7,79,131],"specified":[8],"people":[9],"and":[10,41,52,120,146,155,168,176],"objects,":[11],"then":[12],"continues":[13],"it":[14],"under":[15],"changing":[16,118],"instructions.":[17],"We":[18],"introduce":[19],"TaoMate-R1,":[20],"streaming":[22,171],"generator":[24],"that":[25],"organizes":[26],"adaptation":[27,163],"parameters":[28,164],"through":[29,65],"temporal":[30,148],"role":[31],"specialization.":[32],"It":[33,140],"assigns":[34],"separate":[35],"low-rank":[36],"adapters":[37],"to":[38,133],"establishment":[40,167],"continuation":[42,169],"on":[43],"frozen":[45],"backbone.":[46],"Each":[47],"adapter":[48],"performs":[49],"both":[50],"denoising":[51,78],"context":[53,80],"writing":[54,81],"for":[55,170],"its":[56],"role;":[57],"Self":[58],"Gradient":[59],"Forcing":[60],"jointly":[61],"trains":[62],"the":[63,66,90,95,105,108,126],"roles":[64],"history":[67],"they":[68],"construct.":[69],"This":[70],"allocation":[71],"contrasts":[72],"with":[73,117,135],"operation-based":[74],"specialization,":[75],"which":[76],"separates":[77],"across":[82,150],"all":[83],"chunks.":[84],"A":[85],"fixed-replay":[86],"gradient":[87],"analysis":[88],"characterizes":[89],"update":[91],"directions":[92],"admitted":[93],"by":[94,165],"two":[96],"sharing":[97],"schemes.":[98],"On":[99],"32":[100],"cases,":[102],"we":[103],"compare":[104],"schemes":[106],"at":[107,180],"same":[109],"two-adapter":[110],"budget.":[111],"Across":[112],"ten":[113],"approximately":[114],"two-minute":[115],"streams":[116],"instructions":[119],"shared":[121],"teacher-audio":[122],"conditioning,":[123],"TaoMate-R1":[124],"reduces":[125],"mean":[127,144],"boundary":[128,137],"luminance":[129],"jump":[130],"1.96":[132],"0.613,":[134],"higher":[136,143],"feature":[138],"similarity.":[139],"also":[141],"achieves":[142],"CLIP":[145],"DINO":[147],"similarity":[149],"short":[151],"interactions,":[152],"long":[153],"streams,":[154],"public":[156],"reference":[157],"compositions.":[158],"These":[159],"results":[160],"support":[161],"grouping":[162],"generation.":[173],"Our":[174],"code":[175],"model":[177],"are":[178],"released":[179],"https://github.com/TaoLiveAIGC/TaoMate-H3.":[181]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}