一作ACL 2026Poster· Natural Language Processing
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
Shun Zou · Yong Wang · Zehui Chen · Lin Chen · Chongyang Tao · Feng Zhao · Xiangxiang Chu
摘要
Diffusion Large Language Models (dLLMs) have recently become a promising alternative to autoregressive large language models (ARMs). Semi-autoregressive (Semi-AR) decoding is widely employed in base dLLMs and advanced decoding strategies due to its superior performance. However, our observations...