3 papers
cs.LG2026
Partially Linear Autoencoders for Manifold Learning and Dimensionality Reduction
Louen Pottier, Louis Lesueur, Anders Thorin
Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear encoders and decoders, we invest…
cs.CV2026
LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting
Louen Pottier
We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular videos. At inference it lets…
cs.LG2021
Deep Surrogate for Direct Time Fluid Dynamics
Lucas Meyer, Louen Pottier, Alejandro Ribes +1
The ubiquity of fluids in the physical world explains the need to accurately simulate their dynamics for many scientific and engineering applications. Traditionally, well establish…