Learned numerical methods for linear algebra and optimization Learning components of numerical algorithms, such as preconditioners, warm starts and inner solvers, to accelerate them without sacrificing reliability. Bayesian experimental design for self-driving labs Methods for choosing the next experiment, deployed in autonomous laboratories for materials science. Diffusion and generative models Developing and applying diffusion-based generative models for conditional inference, image restoration, and scientific applications. Computational medicine Machine learning and optimization for radiotherapy, medical imaging, and drug discovery.
