一作ICML 2026Poster· Deep Learning / Large Language Models
DFlash: Block Diffusion for Flash Speculative Decoding
Jian Chen · Yesheng Liang · Zhijian Liu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Jian Chen · Yesheng Liang · Zhijian Liu
Yutao Sun · Tianzhu Ye · Li Dong · Yuqing Xia · Jian Chen · Yizhao Gao · Shijie Cao · Jianyong Wang · Furu Wei
Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade generation quality. In this work, we propose Rectified Sparse At...