2026
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
ICLR 2026poster
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a single iteration. However, none of the existing open-source dLLMs have achieved superior inference speed over AR LLMs of…