Leyang Xue

School of Informatics, The University of Edinburgh

prof_pic.jpg

Moody 31,

Largs, Scotland

Actively seeking Systems & AI positions in research and industry.

I am currently a Research Associate at The University of Edinburgh. I was a PhD Student at The University of Edinburgh, supervised by Prof. Mahesh Marina and Prof. Luo Mai. I received my B.Eng. degree in Electronic and Computer Engineering from Shanghai Jiao Tong University in Aug. 2018.

My research interest lies in the intersection of machine learning and distributed systems. My goal is to build efficient systems for the large-scale machine learning jobs. My current research focuses on the cost and energy efficiency of inference and training large language models (LLMs) in both cloud and edge environment. My current postdoc research focuses on AI on Edge Infra and GPU sharing between AI and realtime workload.

News

Jun 25, 2026
EdgeSys 2026 Best Paper Award

Received the EdgeSys 2026 Best Paper Award for Morphling: Emulator for Distributed Machine Learning at the Edge.

Selected Publications

  1. SIGCOMM
    CausalTune: Causal Learning based Automated Cellular RAN Configuration Tuning Framework
    Leyang Xue, Bolun Zhang, Yibo Ma, Mahesh Marina , He Yan, Yu Zhou, Cheuk Yiu Ip, Senthil Dhandapani, and 1 more author
    In SIGCOMM, 2026
  2. BatchGen: An Architecture for Scalable and Efficient Batch Inference
    Tairan XuLeyang Xue, Zhan Lu, Jinfu Deng, Hongyang Xiao, Yinsicheng Jiang, Congjie He, Matej Sandor, and 2 more authors
    In OSDI, 2026
  3. EdgeSys
    Morphling: Emulator for Distributed Machine Learning at the Edge
    Leyang Xue, Yufeng Xia, Eren Mendi, Ismaeel Bashir, Jiaxun Yang, Myungjin Lee, and Mahesh K. Marina
    In EdgeSys, 2026
  4. ServerlessLLM: Low-Latency Serverless Inference for Large Language Models
    Yao FuLeyang XueYeqi Huang, Andrei-Octavian Brabete, Dmitrii UstiugovYuvraj Patel, and Luo Mai
    In OSDI, 2024
  5. Towards Energy Efficient 5G vRAN Servers
    In NSDI, 2025