Haodong Zheng

PhD student · EPFL

Portrait of Haodong Zheng

I'm a second year PhD student at EPFL, working with Prof. Sanidhya Kashyap. Before that, I was a research intern in the Paul G. Allen School of Computer Science & Engineering at the University of Washington in Seattle, advised by Prof. Baris Kasikci and Prof. Yigong Hu.

My current research focuses on agentic RL training systems, with an emphasis on efficient resource management and scheduling. Specifically, I explore new systems principles and abstractions for large-scale agentic RL training of MLLMs and VLAs, with the goal of improving end-to-end performance without compromising model convergence.

I am always looking for motivated undergraduate and master students to collaborate on exciting research projects. If my research interests resonate with you, please fill out this form and send me an email.

Research Experiences

EDIC, EPFL

2025/09-Now

Ph.D. student

Focus on large-scale agentic RL training systems.

Systems lab, University of Washington

2024/01-2025/07

Research Intern

Focused on system reliability and AI for systems.

Selected Publications

  1. Diagnosing Performance Issues in Application-Defined Resources

    Yigong Hu, You-Liang Huang, Haodong Zheng, Yicheng Liu, Dedong Xie, Baris Kasikci

    20th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2026)