Generative design of molecules and materials

Nature conceals the principles governing molecular and materials function within combinatorial spaces too vast to explore exhaustively. Progress in materials discovery thus depends on learning from limited data how composition and structure give rise to desired properties. Generative AI offers a principled approach by casting the problem as learning a transport map from a simple base distribution to the distribution of chemically valid structures, enabling both unconditional discovery and generation conditioned on target properties. In this talk, I will present Open Materials Generation (OMatG) and PropMolFlow, state-of-the-art generative frameworks for inorganic crystals and small molecules. I will then show how policy-gradient reinforcement learning can be extended to flow-based generative models, and use it to optimize OMatG for target properties at inference time, dramatically improving crystal structure prediction. Finally, I will discuss how these ideas extend to molecular crystals.