Generative models are increasingly used to produce novel scientific data, including crystal structures. In this talk, I will present two methods leveraging generative models for materials discovery. First, I will talk about UniMat, a unified crystal structure representation, which enables scalable generation of high-fidelity crystal structures using diffusion models. Second, I will introduce Generative Hierarchical Materials Search (GenMS), which uses natural language input, diffusion models, and graph neural networks to generate viable crystal structures. These methods represent a step forward in enabling scalable and efficient materials discovery with generative models.
Biography:
Dr. Sherry Yang is an incoming assistant professor of Computer Science at NYU Courant, a post-doc at Stanford University, and a research scientist at Google DeepMind. Her research aims to develop machine learning models with internet-scale knowledge to make better-than-human decisions. To this end, her work has pioneered generative modeling techniques coupled with algorithms for planning and reinforcement learning, and their applications in robotics and materials science. Her research UniSim: Learning Interactive Real-World Simulators has been recognized by the Outstanding Paper award at ICLR. Prior to her current roles, Sherry received her PhD in Computer Science at UC Berkeley and her Bachelor's and Master’s degree in Electrical Engineering and Computer Science at MIT.
Cory 373