Siyuan Chen

Welcome to you, and also welcome to me!

I’m a CS Ph.D. student at the University of British Columbia, advised by Prof. Peter Yichen Chen.

My research develops AI foundation models for protein structure, interaction, and dynamics, combining geometric deep learning, physics-grounded priors, and large-scale molecular dynamics data. I am particularly interested in (i) physically valid biomolecular generation, (ii) scalable protein–protein interaction discovery, and (iii) Transformer-based neural simulators that learn protein conformational dynamics from MD trajectories. More broadly, I work on neural surrogate models for physical dynamics, at the intersection of computer graphics, scientific computing, and machine learning.

I graduated from Shanghai Jiao Tong University with a B.S. degree in Physics and a minor in Computer Science.

Before starting my Ph.D., I interned at SJTU DA Lab, where I worked with Prof. Xubo Yang and Ph.D. student Hui Wang, and also collaborated remotely with Bo Zhu. I also worked at DMCV with Prof. Ran Yi. From September 2024 to December 2024, I was an exchange student at the University of Toronto, where I worked with Zhecheng and Prof. Eitan Grinspun.

news


Sep 27, 2026	WorldAgent preprint is out on arXiv !
Sep 23, 2026	WorldContact preprint is out on arXiv !
Sep 1, 2026	WorldParticle has been accepted to SIGGRAPH Asia 2026 (Conference Track) !
Jul 8, 2026	My advisor Prof. Peter Yichen Chen received the Early Career Researcher Award at SCA 2026 !
Jul 8, 2026	Presented Closing Trajectories at SCA 2026 in Barcelona !
May 22, 2026	Closing Trajectories preprint is out on arXiv !
May 1, 2026	WorldParticle preprint is out on arXiv !
Mar 1, 2026	Factorized Neural Implicit DMD preprint is out on arXiv !
Jan 26, 2026	One paper has been accepted to ICLR 2026 !
Jan 16, 2026	SG-Splatting has been accepted to ICASSP 2026 !
Apr 1, 2025	One paper has been conditionally accepted to Siggraph 2025 !
Mar 27, 2025	Start journey as a Ph.D. student in Computer Science at the University of British Columbia !

selected publications

WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer

Caoliwen Wang^*, Minghao Guo^*^†, Siyuan Chen^*, Heng Zhang, Mengdi Wang, Xingyu Ni, Hanson Sun, Kunyi Wang, Zherong Pan, Kui Wu, Lingjie Liu, Yin Yang, Chenfanfu Jiang, Taku Komura, Wojciech Matusik, Peter Yichen Chen^†

SIGGRAPH Asia (Conference Track) 2026

PDF Website
WorldAgent: Verification-Guided Agentic Physical World Construction

Caoliwen Wang^*, Mengdi Wang^*^†, Yige Chen^*, Zejia Wu, Bowen Huang, Siyuan Chen, Guanxiong Chen, Lifu Wei, Heng Zhang, Qinghai Zhang, Yin Yang, Guandao Yang, Shiying Xiong, Peng Wang, Chenfanfu Jiang, Peter Yichen Chen

Preprint, arXiv:2609.33208 2026

PDF
WorldContact: A Contact-Centric World Model for Scalable Robot Learning

Caoliwen Wang, Mengdi Wang^†, Heng Zhang, Shixun Huang, Siyuan Chen, Chao Liu, Anpei Chen, Zhendong Wang, Peter Yichen Chen^†, Huamin Wang

Preprint, arXiv:2609.19600 2026

PDF
Closing Trajectories: Equation-Free Cyclic Animation via Koopman Surrogates

Shixun Huang, Siyuan Chen, Yue Chang, Zhecheng Wang, Peter Yichen Chen

ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA), Computer Graphics Forum 2026

Project Webpage PDF
Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection

Siyuan Chen^*, Minghao Guo^*^†, Caoliwen Wang, Anka He Chen, Yikun Zhang, Jingjing Chai, Yin Yang, Wojciech Matusik, Peter Yichen Chen^†

International Conference on Learning Representations (ICLR) 2026

PDF
Factorized Neural Implicit DMD for Parametric Dynamics

Siyuan Chen^*, Zhecheng Wang^*, Yixin Chen, Yue Chang, Peter Yichen Chen, Eitan Grinspun, Jonathan Panuelos^†

Preprint, arXiv:2603.10995 2026

PDF
Fast Subspace Fluid Simulation with a Temporally-Aware Basis

Siyuan Chen, Yixin Chen, Jonathan Panuelos, Otman Benchekroun, Yue Chang, Eitan Grinspun, Zhecheng Wang^†

ACM SIGGRAPH Conference Papers 2025

Project Webpage PDF