Hello, I'm Zirui Wang

2nd-year PhD Student in Computer Science

Research interests in machine learning systems and storage systems. Working on building efficient and scalable systems for next-generation data-intensive applications.

Zirui Wang

Zirui Wang

CS PhD Student

About Me

I am a PhD student in Computer Science at the University of Virginia, working under the supervision of Prof. Yue Cheng in the DS2 Lab. My research interests include machine learning systems, cache systems, and distributed systems. I am dedicated to building efficient and scalable systems for next-generation data-intensive applications.

My research focuses on addressing challenges in real-world storage systems, driven by the complexities of modern data-intensive computer systems. I am particularly interested in serverless AI, storage systems for AI, and serverless computing using an end-to-end approach that spans applications, middleware, platforms, and low-level operating systems.

Education

2024 - Present

PhD in Computer Science

University of Virginia

2022 - 2024

MS in Computer Science

Boston University

2018 - 2022

BS in Computer Science

Hangzhou Dianzi University

Publications

2025

"Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing"

Zhaoyuan Su, Tingfeng Lan, Zirui Wang, Juncheng Yang, Yue Cheng

Preprint

2025

"Towards Efficient LLM Storage Reduction via Tensor Deduplication and Delta Compression"

Zirui Wang, Tingfeng Lan, Zhaoyuan Su, Juncheng Yang, Yue Cheng

23rd USENIX Symposium on Networked Systems Design and Implementation (NSDI 2026)

2024

"Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask"

Zhaoyuan Su, Ammar Ahmed, Zirui Wang, Ali Anwar, Yue Cheng

50th International Conference on Very Large Data Bases (VLDB 2024)

2021

"Temporal Cue Guided Video Highlight Detection with Low-Rank Audio-Visual Fusion"

Qinghao Ye*, Xiyue Shen*, Yuan Gao*, Zirui Wang*, Qi Bi, Ping Li, Guang Yang

International Conference on Computer Vision (ICCV 2021)