{"id":"https://openalex.org/W4415537863","doi":"https://doi.org/10.1145/3746027.3755713","title":"AV-DiT: Taming Image Diffusion Transformers for Efficient Joint Audio and Video Generation","display_name":"AV-DiT: Taming Image Diffusion Transformers for Efficient Joint Audio and Video Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537863","doi":"https://doi.org/10.1145/3746027.3755713"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755713","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755713","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755713","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kai Wang","orcid":"https://orcid.org/0009-0005-3655-224X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0005-3655-224X","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028337614","display_name":"Shijian Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shijian Deng","raw_affiliation_strings":["University of Texas at Dallas, Richardson, USA"],"raw_orcid":"https://orcid.org/0009-0008-9560-702X","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692560","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0002-4509-0535"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["Adobe Systems, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-4509-0535","affiliations":[{"raw_affiliation_string":"Adobe Systems, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041117623","display_name":"Dimitrios Hatzinakos","orcid":"https://orcid.org/0000-0003-3345-9232"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dimitrios Hatzinakos","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3345-9232","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101835756","display_name":"Yapeng Tian","orcid":"https://orcid.org/0000-0003-1423-4513"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yapeng Tian","raw_affiliation_strings":["University of Texas at Dallas, Richardson, USA"],"raw_orcid":"https://orcid.org/0000-0003-1423-4513","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"10486","last_page":"10495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9980000257492065,"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":0.6258000135421753},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3587000072002411},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33219999074935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731000185012817},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6258000135421753},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45649999380111694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755713","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755713","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755713","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755713","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2760103357","https://openalex.org/W2963524571","https://openalex.org/W3015371781","https://openalex.org/W3176445421","https://openalex.org/W4312633146","https://openalex.org/W4312651322","https://openalex.org/W4312933868","https://openalex.org/W4386071707","https://openalex.org/W4386075767","https://openalex.org/W4390872297","https://openalex.org/W4393147998","https://openalex.org/W4400580599","https://openalex.org/W4403792339"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Diffusion":[1],"Transformers":[2],"(DiTs)":[3],"have":[4],"shown":[5],"impressive":[6],"capabilities":[7],"in":[8,170],"generating":[9],"single-modality":[10],"content,":[11],"including":[12],"images,":[13],"videos,":[14],"and":[15,39,58,88,153],"audio.":[16],"However,":[17],"the":[18,83,91,107,122,128,141,161],"potential":[19],"of":[20,85,118],"DiTs":[21],"to":[22,45,126],"enable":[23],"superb":[24],"multimodal":[25],"content":[26],"creation":[27],"remains":[28],"underexplored.":[29],"To":[30,54],"bridge":[31],"this":[32],"gap,":[33],"we":[34],"introduce":[35],"AV-DiT,":[36],"a":[37,64,95,101,115,184,197],"novel":[38],"efficient":[40],"audio-visual":[41,172],"diffusion":[42],"transformer":[43],"designed":[44],"generate":[46],"high-quality,":[47],"realistic":[48],"videos":[49],"with":[50,72,145,174,190],"synchronized":[51],"audio":[52,87,132,152],"tracks.":[53],"minimize":[55],"model":[56],"complexity":[57],"computational":[59],"costs,":[60],"our":[61,165,180],"AV-DiT":[62,166],"utilizes":[63],"modality-shared":[65],"DiT":[66,103,124,142],"backbone":[67,81,189],"pre-trained":[68,102],"on":[69,160],"image-only":[70],"data,":[71],"only":[73],"newly":[74],"inserted":[75],"adapters":[76],"being":[77],"trainable.":[78],"This":[79],"shared":[80,136,186],"facilitates":[82,148],"generation":[84,173],"both":[86],"video.":[89],"Specifically,":[90],"video":[92,111],"branch":[93],"incorporates":[94],"trainable":[96,119],"temporal":[97,108],"attention":[98],"layer":[99],"into":[100],"block":[104,125,138],"for":[105,110,131,156,195],"capturing":[106],"consistency":[109],"generation.":[112,133],"In":[113],"addition,":[114],"small":[116],"number":[117],"parameters":[120],"adapt":[121],"image-based":[123],"learn":[127],"acoustic":[129],"characteristics":[130],"An":[134],"extra":[135],"self-attention":[137],"reused":[139],"from":[140],"block,":[143],"equipped":[144],"lightweight":[146],"parameters,":[147],"feature":[149],"interaction":[150],"between":[151],"visual":[154],"modalities":[155],"alignment.":[157],"Extensive":[158],"experiments":[159],"datasets":[162],"demonstrate":[163],"that":[164,183],"achieves":[167],"state-of-the-art":[168],"performance":[169],"joint":[171,198],"significantly":[175],"fewer":[176],"tunable":[177],"parameters.":[178],"Furthermore,":[179],"results":[181],"highlight":[182],"single":[185],"image":[187],"generative":[188],"modality-specific":[191],"adaptations":[192],"is":[193],"sufficient":[194],"constructing":[196],"audio-video":[199],"generator.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}