Saiyue Lyu
she/her/hers
I am a Computer Science Ph.D. student at the University of British Columbia supervised by Prof. Mathias Lécuyer. My research focuses on understanding how AI systems make decisions and how we can make those decisions more reliable, interpretable, and aligned with human goals. I work at the intersection of trustworthy AI, AI agents, diffusion models, reasoning, and formal methods for understanding and improving modern machine learning systems. My long-term goal is to develop principled approaches that help AI systems operate more reliably in complex real-world environments.
I obtained my master degree at the University of Waterloo supervised by Prof. Mark Giesbrecht working on mathematical algorithms and symbolic computation. I completed my undergraduate degree at Waterloo in Pure Mathematics and Combinatorics & Optimization, where I was fortunate to work with Prof. Yu-Ru Liu. I also worked with Prof. Zhicong Lu on HCI and Computational Social Science. I have also interned at RBC Borealis and Amazon, where I worked on diffusion-based time series forecasting and experience-guided graph reasoning agent, respectively.
Education
PhD, University of British Columbia, Computer Science, 2022.9-present
MMath, University of Waterloo, Computer Science, thesis-based, co-op option, 2020.1-2022.4 (Master Thesis, Slides)
BMath, University of Waterloo, Honors Pure Mathematics, Honors Combinatorics and Optimization, 2016.9-2019.12