HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Tue, 11 Nov 2025 20:25:04 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"69139ba0-2422" expires: Mon, 29 Dec 2025 12:21:11 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: B30B:318CF6:8B7CF3:9CB3CE:69526FDF accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 12:11:11 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210072-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767010272.694679,VS0,VE215 vary: Accept-Encoding x-fastly-request-id: 2b098701352fb8d2ecf118c521f821f5671a1c97 content-length: 2075

JavisDiT:

Joint Audio-Video Diffusion Transformer with
Hierarchical Spatio-Temporal Prior Synchronization

Kai Liu^1,2, Wei Li³, Lai Chen¹, Shengqiong Wu², Yanhao Zheng¹, Jiayi Ji²,
Fan Zhou¹, Rongxin Jiang¹, Jiebo Luo⁴, Hao Fei^2*, Tat-Seng Chua²,

¹ Zhejiang University, ² National University of Singapore,
³ University of Science and Technology of China, ⁴ University of Rochester

Work in progress (^*Correspondence)

ArXiv Paper HF Paper Code Model Data Video

JavisDiT has been moved to this URL under the JavisVerse project. Click to see the updates!