46 citations · 50 across the 2 of their papers we have counts for
3 papers
cs.LG2022★ 4 cited
Physics-constrained Unsupervised Learning of Partial Differential Equations using Meshes
Mike Y. Michelis, Robert K. Katzschmann
Enhancing neural networks with knowledge of physical equations has become an efficient way of solving various physics problems, from fluid flow to electromagnetism. Graph neural ne…
cs.RO2022★ 46 cited
Sim-to-Real for Soft Robots using Differentiable FEM: Recipes for Meshing, Damping, and Actuation
Mathieu Dubied, Mike Michelis, Andrew Spielberg +1
An accurate, physically-based, and differentiable model of soft robots can unlock downstream applications in optimal control. The Finite Element Method (FEM) is an expressive appro…
cs.LG2021
On Linear Interpolation in the Latent Space of Deep Generative Models
Mike Yan Michelis, Quentin Becker
The underlying geometrical structure of the latent space in deep generative models is in most cases not Euclidean, which may lead to biases when comparing interpolation capabilitie…