Videos

Start date cannot be after end date.

Sam Eisenstat - Concepts, information, and objectivity

September 2, 2026
IPAM

Christopher Potts - Creating and detecting subliminal learning effects on demand

September 1, 2026
IPAM

Ryan Cotterell - Two views of a language model

September 1, 2026
IPAM

Jacob Steinhardt - Oversight Foundation Models

September 1, 2026
IPAM

Max Tegmark - Neural network interpretability: symmetry, geometry and formal verification

September 1, 2026
IPAM

Bin Yu - Not All Interpretation Methods Are Created Equal: Principled Evaluation of AI Interpretability

September 1, 2026
IPAM

Josh Batson - Interpretability: From Art Towards Science

August 31, 2026
IPAM

Marina Meila - Counterfactual Explanations in the statistical limit

August 31, 2026
IPAM

Paul Christiano - Explaining computational phenomena

August 31, 2026
IPAM

Jacob Hilton - Miniature mathematical mysteries: uninterpreted models with fewer than 1,500 parameters

August 31, 2026
IPAM

Been Kim - Changing Shapes: Interpretability, AI, and the Future of Human Agency

August 31, 2026
IPAM

Yasemin Yildirim - Constructing and classifying Legendrian doubles

August 25, 2026
IPAM