collaborators

7 papers

cs.AI2026

xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim +4

Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative…

cs.AI2026

PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding

Zheng Wang, Zhifan Ye, Qi Cheng +8

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, generating tokens in parallel. This makes them effective draft models f…

cs.LG2026

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Ziyan Wang, Zheng Wang, Xingwei Qu +5

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) of…

cs.CL2024

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

Haoran You, Yichao Fu, Zheng Wang +2

Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention m…

cs.CL2024

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Zheng Wang, Boxiao Jin, Zhongzhi Yu +1

How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate c…

cs.LG2024

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Zhongzhi Yu, Zheng Wang, Yonggan Fu +3

Attention is a fundamental component behind the remarkable achievements of large language models (LLMs). However, our current understanding of the attention mechanism, especially r…