{"id":"https://openalex.org/W7108204506","doi":"https://doi.org/10.48550/arxiv.2511.21780","title":"3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation","display_name":"3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W7108204506","doi":"https://doi.org/10.48550/arxiv.2511.21780"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.21780","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.21780","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Yaoru","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Yaoru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Si, Heyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Heyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Landi, Federico","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Landi, Federico","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gallegos, Pilar Oplustil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gallegos, Pilar Oplustil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Koutsoumpas, Ioannis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koutsoumpas, Ioannis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vazquez, O. Ricardo Cortez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vazquez, O. Ricardo Cortez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fu, Ruiju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Ruiju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guo, Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Shunyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shunyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Song, Mingli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Mingli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"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":0.6669999957084656,"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":0.6669999957084656,"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":0.09380000084638596,"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/T11439","display_name":"Video Analysis and Summarization","score":0.02810000069439411,"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/transformer","display_name":"Transformer","score":0.6736000180244446},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.47029998898506165},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.45890000462532043},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37630000710487366},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.3434999883174896},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.323199987411499},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990000247955322},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6736000180244446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.26429998874664307},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.21780","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.21780","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-video":[0],"(T2V)":[1],"diffusion":[2,98],"models":[3,107],"have":[4],"recently":[5],"achieved":[6],"impressive":[7],"visual":[8],"quality,":[9],"yet":[10],"most":[11],"systems":[12],"still":[13],"generate":[14],"silent":[15],"clips":[16],"and":[17,40,63,76,83,110,133,146,161,180,188],"treat":[18],"audio":[19,109,118,145,182],"as":[20,112,144],"a":[21,95,121,164,192],"secondary":[22],"concern.":[23],"Existing":[24],"audio-video":[25,48,103,159,186],"generation":[26],"pipelines":[27],"typically":[28],"decompose":[29],"the":[30,130,141],"task":[31],"into":[32],"cascaded":[33],"stages,":[34],"which":[35],"accumulate":[36],"errors":[37],"across":[38,129,191],"modalities":[39],"are":[41],"trained":[42],"under":[43],"separate":[44],"objectives.":[45],"Recent":[46],"joint":[47],"generators":[49],"alleviate":[50],"this":[51],"issue":[52],"but":[53],"often":[54],"rely":[55],"on":[56,158],"dual-tower":[57],"architectures":[58],"with":[59],"ad-hoc":[60],"cross-modal":[61],"bridges":[62],"static,":[64],"single-shot":[65],"text":[66,111,137,142],"conditioning,":[67],"making":[68],"it":[69],"difficult":[70],"to":[71,77],"both":[72],"reuse":[73],"T2V":[74,122,166],"backbones":[75],"reason":[78],"about":[79],"how":[80],"audio,":[81],"video":[82,147],"language":[84],"interact":[85],"over":[86],"time.":[87],"To":[88],"address":[89],"these":[90],"challenges,":[91],"we":[92],"propose":[93],"3MDiT,":[94],"unified":[96],"tri-modal":[97,124,189],"transformer":[99],"for":[100],"text-driven":[101],"synchronized":[102],"generation.":[104],"Our":[105],"framework":[106],"video,":[108],"jointly":[113],"evolving":[114],"streams:":[115],"an":[116,134],"isomorphic":[117],"branch":[119],"mirrors":[120],"backbone,":[123],"omni-blocks":[125],"perform":[126],"feature-level":[127],"fusion":[128],"three":[131],"modalities,":[132],"optional":[135],"dynamic":[136],"conditioning":[138],"mechanism":[139],"updates":[140],"representation":[143],"evidence":[148],"co-evolve.":[149],"The":[150],"design":[151],"supports":[152],"two":[153],"regimes:":[154],"training":[155],"from":[156],"scratch":[157],"data,":[160],"orthogonally":[162],"adapting":[163],"pretrained":[165],"model":[167],"without":[168],"modifying":[169],"its":[170],"backbone.":[171],"Experiments":[172],"show":[173],"that":[174],"our":[175],"approach":[176],"generates":[177],"high-quality":[178],"videos":[179],"realistic":[181],"while":[183],"consistently":[184],"improving":[185],"synchronization":[187],"alignment":[190],"range":[193],"of":[194],"quantitative":[195],"metrics.":[196]},"counts_by_year":[],"updated_date":"2025-12-03T00:07:38.036990","created_date":"2025-12-03T00:00:00"}
