Geometric Deep Learning

We are exploring methods of Geometric Deep Learning, especially Graph Neural Networks, to accurately model physical processes from meshes and point clouds in both supervised and reinforcement learning settings.

New Paper @ ICLR23 Grounding Graph Network Simulators using Physical Sensor Observations

Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned Graph Network Simulators produced accurate mesh-based simulations while requiring only a fraction of the computational cost of traditional simulators.