Wei Zhang

I am a first-year M.S. student in Computer Science at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Fan Lai. I received my B.S. in Computer Science from Peking University, where I was fortunate to collaborate with Prof. Xin Jin.

My research interests lie broadly in machine learning systems (MLSys), particularly in large language model (LLM) serving, scheduling, and system optimization.
I am interested in building efficient, SLO-aware inference systems that can bridge the gap between model performance and practical serving constraints.

Recently, my exploration has expanded toward world models and video generation systems, where I study how system-level design — such as memory management, asynchronous interaction, and consistency optimization — can enhance the scalability and fidelity of generative models in dynamic environments.