(1) AI for large-scale scientific simulations, design, and control (for fluid dynamics, aerospace engineering, mechanical engineering, materials science, life sciences) using generative models and foundation models;
(2) AI for scientific discovery (for life sciences and physics);
(3) Representation learning with graph neural networks, generative models, and information theory
We introduce a novel method for controlling complex physical systems using generative models, by minimizing the learned generative energy function and specified objectiveRead More