One Block Ahead: Promoting Sampler State in Diffusion Language Models
It is demonstrated that for uniform-state diffusion LMs, where a block's denoising progress is not visible in its intermediate tokens, concurrent decoding is advantageous if the next block's tokens are promoted together with the corresponding sampler state, including the self-conditioning signal and the denoising time.
Yang-Yi Shen, Pin-Jui Ku, Nicolai Oswald et al.
· 0 citations