Bei Ouyang

Bei Ouyang

PhD Student

University of Texas at Austin

Research Interests

Systems for ML
Efficient ML
Algorithm-System Co-design

About

I am a first-year Ph.D. student in Computer Science at UT Austin, co-advised by Prof. Aditya Akella and Prof. Zhangyang (Atlas) Wang. My research focuses on algorithm–system co-design for efficient machine learning systems.

Prior to that, I received my M.S. and B.E. degrees in Computer Science from Sun Yat-sen University, advised by Prof. Xu Chen. My previous work focused on edge intelligence and resource-efficient LLMs.

News

2026-03

🎉 One paper get accepted at SIGMETRICS'26!

2026-01

🎉 One paper get accepted at TPDS!

2025-12

🎉 One paper get accepted at Infocom’26!

2025-05

🎉 One paper get accepted at at TMC!

2025-04

🎉 One paper get accepted at at TIFS!

2024-12

🎉 One paper get accepted at Infocom’25!

2024-06

🎉 One paper get accepted at ICPP’24!

Selected Publications

View All →

* indicates equal contribution

UniCache: Unifying Prefix Cache Eviction for Heterogeneous LLM Serving Workloads

Bei Ouyang, Yifan Qiao, Jiarong Xing

Proceedings of the ACM on Measurement and Analysis of Computing Systems (SIGMETRICS) 2026

Jupiter: Fast and resource-efficient collaborative inference of generative llms on edge devices

Shengyuan Ye, Bei Ouyang, Liekang Zeng, Tianyi Qian, Xiaowen Chu, Jian Tang, Xu Chen

IEEE INFOCOM 2025-IEEE Conference on Computer Communications (INFOCOM) 2025

Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-tuning

Bei Ouyang*, Shengyuan Ye*, Liekang Zeng, Tianyi Qian, Jingyi Li, Xu Chen

Proceedings of the 53rd International Conference on Parallel Processing (ICPP) 2024