Francois Lanusse

Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

AION-1: Omnimodal Foundation Model for Astronomical Sciences

Multiple Physics Pretraining for Spatiotemporal Surrogate Models

Learning Diffusion Priors from Observations by Expectation Maximization

Multiple Physics Pretraining for Physical Surrogate Models

xVal: A Continuous Number Encoding for Large Language Models