AI Alliance
Materials and Chemistry Webinar Series

Thursday May 15th

10:00–11:00 AM EST

Online: Meeting Link Provided via Email

Topic: Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

Many scientific tasks, such as protein engineering and small-molecule drug discovery, can be formulated as conditional generation problems over discrete spaces. This talk introduces a new approach that enables tractable classifier and classifier-free guidance on discrete state-space diffusion and flow models. I will demonstrate how this method can be applied for conditional generation tasks in protein sequence, small-molecule graph, and DNA sequence design.

• Speaker: Hunter Nisanoff recently graduated from his PhD in Computational Biology from UC Berkeley where he was advised by Professor Jennifer Listgarten. His research focuses on machine learning methods for protein engineering. Prior to his PhD, Hunter worked at D. E. Shaw Research developing machine learning and simulation-based methods for small-molecule drug discovery.

Want a deep dive? 

• https://arxiv.org/abs/2406.01572

Registration 

​The AI Alliance is a collaborative global community committed to advancing open, safe, and responsible artificial intelligence. We are technology creators, adopters, researchers, and policymakers working to maximize AI’s benefits to people everywhere. We focus on building open technologies, advocating for ethical AI practices, and fostering global collaboration while enhancing AI's foundational capabilities and societal trust.