I'm a first-year Computer Science PhD student at the University of British Columbia, advised by Peter Yichen Chen. I received my BSc in Mathematics and Computer Science from the University of Toronto, where I was fortunate to be advised by Professors Jude Kong and Eitan Grinspun. Previously, I was a member of the DGP Lab, where I worked with Yue Chang, a wonderful mentor and friend.
I work on Physics AI: integrating physical principles with learning methods to build scalable, stable, and generalizable models via data-assisted optimization of differential/integral equations that preserve physical structure.
Email / CV / GitHub / LinkedIn / Google Scholar
WorldContact: A Contact-Centric World Model for Scalable Robot Learning
Caoliwen Wang, Mengdi Wang, Heng Zhang, , Siyuan Chen, Chao Liu, Anpei Chen, Zhendong Wang, Peter Yichen Chen, Huamin Wang
arXiv preprint arXiv:2609.19600, 2026
WorldContact learns contact-aware deformable-object dynamics from limited high-quality trajectories, generating robot-policy training data with 10× faster state rollouts and improving real-robot bag-lifting success from 65% to 95%.
Closing Trajectories: Equation-Free Cyclic Animation via Koopman Surrogates
, Siyuan Chen, Yue Chang, Zhecheng Wang, Peter Yichen Chen
ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA), 2026
Closing Trajectories formulates cyclic animation as a numerical optimization problem, solving for periodic controls under hard temporal constraints through a Koopman surrogate.
Odd-DC: Generalizable Neural Model Reduction via Odd Difference-of-Convex Structure
, Eitan Grinspun, Yue Chang
Conditionally accepted for publication in a leading computer graphics journal, 2026
Odd-DC uses convexity and odd symmetry to generalize neural model reduction to unseen loads, while preserving compact latent spaces and real-time performance.
A systematic review of mathematical and machine learning models of Avian Influenza
, Nicola Luigi Bragazzi, Zahra Movahedi Nia, Murray Gillies, Emma Gardner, Doris Leung, Itlala Gizo, Jude D. Kong
One Health, 2025
A systematic review of mathematical, statistical, and machine learning models for understanding Avian Influenza dynamics, forecasting outbreaks, and evaluating intervention strategies.
No publication matches this topic yet.
Apr 2025 - Present
Undergraduate Research Assistant
Advisors: Eitan Grinspun, Yue Chang
Developing input-convex model reduction methods for physics-based simulation.
Jun 2024 - Dec 2025
Undergraduate Research Assistant
Advisor: Jude Dzevela Kong
Built epidemiological models with Bayesian inference for infectious disease dynamics.