Publications 📚


Conference(*Equal contribution, †Corresponding author)

2025
Memoir: Efficient KV Cache Optimization for LLM Inference in WebAssembly Runtimes
Under review at ACM International Conference on Architectural Support for Programming Languages and Operating Systems(ASPLOS) 2026
Authors: Zirui Wang, Yudan Long, Yuxin Su†, Dan Li, and Zibin Zheng
Access to our work.
An Empirical Study of User-Reported Failures in Open-Source LLMs: Symptoms, Root Causes, and Lessons Learned
Under review at The ACM International Conference on the Foundations of Software Engineering(FSE) 2026
Authors: Guangba Yu∗, Zirui Wang∗, Yujie Huang, Renyi Zhong, Yuedong Zhong, Yilun Wang and Michael R. Lyu†
Access to our work.