Incremental Potential Contact (IPC) is for robust and accurate time stepping of nonlinear elastodynamics. IPC guarantees intersection- and inversion-free trajectories regardless of materials, time-step sizes, velocities, or deformation severity.

Code for the paper "Thermodynamics-informed graph neural networks" published in IEEE Transactions on Artificial Intelligence (TAI).

[ECCV 2024] Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians

IsoGCN code for ICLR2021

PENN code for NeurIPS 2022

[NeurIPS 2022] The implementation for the paper "Learning Physical Dynamics with Subequivariant Graph Neural Networks".

[NeurIPS2024] DiffPhyCon uses generative models to control complex physical systems

Open source implemention of Moving Particle Semi-implcit (MPS) method

[ICLR24] CinDM uses compositional generative models to design boundaries and initial states significantly more complex than the ones seen in training for physical simulation

An extensible benchmark suite to evaluate data-driven physical simulation

Code for the paper "Structure-preserving neural networks" published in Journal of Computational Physics (JCP).

mpm_solver

[AAAI24] LE-PDE-UQ endows deep learning-based surrogate models with robust and efficient uncertainty quantification capabilities for both forward and inverse problems.

Code for the paper "Deep learning of thermodynamics-aware reduced-order models from data" published in Computer Methods in Applied Mechanics and Engineering (CMAME).

Applications of the Teg differentiable programming language to problems spanning graphics and physical simulation.

Source files for my experiments not limited to computer graphics.

Implementation of CogSci 2019 paper 'Active physical learning via reinforcement learning'

Wavelet Diffusion Neural Operator (WDNO) uses diffusion models for generative PDE simulation and control.

This is our course homework. I create a physical simulation program to demonstrate the dynamics of human hair under the influence of air flow.

Visualize different modules related to motor control and operations.