(1) Generative AI for scientific simulation, control, and design: Develop generative AI methods based on diffusion models, flow matching, and next-generation generative models for the simulation, control, and design of large-scale scientific systems. Applications include critical fields such as fluid dynamics, energy systems, mechanical engineering, and life sciences.
(2) AI Agents for scientific discovery: Create machine learning approaches integrating AI agents, representation learning, and foundation models to build general-purpose AI scientists. These systems will enable intelligent automation of scientific experiments and generate new scientific discoveries, with applications in life sciences and physics.
(3) Representation learning with graph neural networks, generative models, and information theory, motivated by scientific applications.
We propose a diffusion method with an asynchronous denoising schedule for physical systems control tasks. It achieves closed-loop control with significant speedup of sampling efficiency.Read More