Ryan Zhiyu An @ UC Merced
I am currently a Postdoctoral Scholar in the Department of Computer Science and Engineering (CSE) at University of California, Merced, School of Engineering. I received my Ph.D. in Electrical Engineering and Computer Science at UC Merced in 2025.
My research lies at the intersection of machine learning, control, and cyber-physical systems, with a focus on the foundations of safe and reliable AI for agricultural and building infrastructures. While many AI systems achieve strong performance in controlled settings, their deployment in real-world settings introduces unmodeled uncertainty, distributional shift, and safety risks that challenge their reliability. My work address the central question:
How do we build AI systems that remain controllable, predictable, aligned with human intent, and robust under distributional shift, so that they can be safely trusted at scale?Â
To this end, my research advances AI safety through uncertainty quantification, robust and risk-aware reinforcement learning, and alignment techniques. The goal is to design systems that are not only high-performing, but also reliable, auditable, and trustworthy at scale.
My work has been published in top venues across AI, ML, Design Automation, Control, and Cyber-Physical Systems including ICLR, AAAI, DAC, KDD, L4DC, BuildSys, and IEEE IoT-J. I received Best Paper Award Runner-Up at BuildSys 2023 and Best Paper Award at HICSS 2025.
Email: zan7 AT ucmerced.edu