keynotes

Keynote #1 | 9:30 am - 10:30 am

Nils Thuerey, Technical University of Munich (TUM)

Title: Probabilistic Simulations: Diffusion Models & Differentiable Solvers

Absract: This talk focuses on the possibilities that arise from recent advances in the area of deep learning for physics simulations. In particular, it will focus on diffusion modeling and numerical solvers which are differentiable. These solvers provide crucial information for deep learning tasks in the form of gradients, which are especially important for time-dependent processes. Also, existing numerical methods for efficient solvers can be leveraged within learning tasks. This paves the way for hybrid solvers in which traditional methods work alongside pre-trained neural network components. In this context, diffusion models and score matching will be discussed as powerful building blocks for training probabilistic surrogates. The capabilities of the resulting methods will be illustrated with examples such as wake flows and turbulent flow cases.

Biography: Nils is an Associate-Professor at the Technical University of Munich (TUM). He focuses on deep-learning methods for physical systems, with an emphasis on fluid flow problems. Together with his research group he’s targeting new methods for the tight and seamless integration of learning algorithms with numerical methods. This encompasses differentiable numerical solvers and architectural inductive biases. He's additionally interested in neural surrogates, learned reduced-order simulations, diffusion models, and visual reconstructions.