Wenrui Huang — accepted AI-conference papers

2025

EPIC: Efficient Position-Independent Caching for Serving Large Language Models

Junhao Hu, Wenrui Huang, Weidong Wang, Haoyi Wang, tiancheng hu, zhang qin +4

ICML 2025poster

Large Language Models (LLMs) show great capabilities in a wide range of applications, but serving them efficiently becomes increasingly challenging as requests (prompts) become more complex. Context caching improves serving performance by reusing Key-Value (KV) vectors, the intermediate representati…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning

Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu +3

ACL 2025finding

Large Language Models (LLMs) have demonstrated strong capabilities across various domains, with recent advancements in challenging reasoning tasks such as mathematics and programming. However, solving reasoning tasks often requires an LLM to generate long sequences, incurring O(N) time and memory co…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗