Foundations of Interpretability - IPAM Foundations of Interpretability - IPAM

Foundations of Interpretability

August 31 - September 4, 2026

Speaker List

Elias Bareinboim (Columbia University)
Josh Batson (Anthropic)
Paul Christiano (Alignment Research Center)
Ryan Cotterell (ETH Zurich)
Jacob Hilton (Alignment Research Center)
Eunice Jun (University of California, Los Angeles (UCLA))
Been Kim (Google DeepMind)
Gitta Kutyniok (Ludwig-Maximilians-Universität München)
Marina Meila (University of Waterloo)
Jacob Mendel (Coefficient Giving)
Gal Mishne (University of California, San Diego (UCSD))
Alexander Oldenziel (Coefficient Giving)
Christopher Potts (Stanford University)
Paul Riechers (Simplex)
Mahdi Soltanolkotabi (University of Southern California (USC))
Jacob Steinhardt (University of California, Berkeley (UC Berkeley))
Terence Tao (University of California, Los Angeles (UCLA))
Max Tegmark (Massachusetts Institute of Technology)
Gyorgy Turan (University of Illinois at Chicago)
Dmitry Vaintrob (Principles of Intelligence, PIBBSS)
Yusu Wang (University of California, San Diego (UCSD))
Michael Winer (The Alignment Research Center)
Bin Yu (University of California, Berkeley (UC Berkeley))