Preprint
Oct 2026
Real-Time Joint Audio-Video Generation by Parallel Adapter Composition
Following the idea of model merging, it is shown that on a packed audio-video backbone the two capabilities can be acquired in parallel, yielding few-step, streaming audio-video whose image quality tracks the bidirectional teacher.
Jing-Yu Li, Xiao-Xiao Xiang, Yi-Wen Guo
· 0 citations