2 papers
cs.LG2026
Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
Omer Rochman-Sharabi, Gilles Louppe
Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary conditions, and observational c…
cs.LG2025
A Neural Material Point Method for Particle-based Emulation
Omer Rochman Sharabi, Sacha Lewin, Gilles Louppe
Mesh-free Lagrangian methods are widely used for simulating fluids, solids, and their complex interactions due to their ability to handle large deformations and topological changes…