Closing Panel + Open Discussion – Speakers: TBD, Moderator: TBD

Closing Panel Fri
October 2, 2026

Do AI models truly learn multiscale physics, and how?

Ching-Yao Lai
October 1, 2026

Panel | Moderator: Hannah Christensen (University of Oxford) with Duncan Watson-Parris (University of California, San Diego), Greg Hakim (University of Washington), Ching-Yao Lai (Stanford University), and Petros Koumoutsakos (Harvard University)

Panel Wed 2
October 1, 2026

Closures for Reduced Order Models Using (appropriately) Reinforcement Learning

Petros Koumoutsakos
October 1, 2026

Probing the Physical Limits of Extreme Events with Differentiable Weather Models

Greg Hakim
October 1, 2026

Gradients, benchmarks, and agents: a new toolkit for old uncertainties

Duncan Watson-Parris
October 1, 2026

Spatial structure and diffusion models

Nisha Chandramoorthy
September 30, 2026

You know it, or you don’t: interpreting compositional behavior in neural models

Naomi Saphra
September 30, 2026

Asking “what-if” with an AI weather model

Maria Molina
September 30, 2026