2026
Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
ICLR 2026poster
Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models, designed for fast parallel generation. However, existing DLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation. We a…