Joshua

A handy toolbox to take the busywork out of text editing.

Official implementation of "OmniForcing: Unleashing Real-time Joint Audio-Visual Generation"[arXiv:2603.11647]. OmniForcing is the first framework to distill bidirectional audio-visual diffusion models into streaming autoregressive generators, enabling real-time joint audio-video generation on a single GPU.

Personal github academic page base on academicpages.github.io

MOVA: Towards Scalable and Synchronized Video–Audio Generation