News

Jul 2026 We received the Best Paper Award for our work, Parameter symmetries determine representational geometry in overparameterized nonlinear networks, at the ICML 2026 Workshop on Weight-Space Symmetries: From Foundations to Practical Applications that took place in Seoul, South Korea, on Friday, July 10, 2026.
Jun 2026 Our work, Parameter symmetries determine representational geometry in overparameterized nonlinear networks, was accepted as an oral presentation at the ICML 2026 Workshop on Weight-Space Symmetries: From Foundations to Practical Applications taking place in Seoul, South Korea, on Friday, July 10, 2026.
May 2026 Our proposal, Adaptive, degenerate, and yet comparable? Rethinking representational comparisons, led by Erin Grant and Lukas Braun, has been accepted as one of three keynote & tutorial sessions at the 9th Annual Conference on Cognitive Computational Neuroscience. The session will take place in New York on Monday, August 3, 2026.
Nov 2024 I am excited to be starting a position as a project research intern at the Gatsby Computational Neuroscience Unit at UCL. Together with Erin Grant, I will work on representational geometry in the Theory of Learning Lab, led by Andrew M. Saxe.
© 2026 Marvin Theiss Last updated on July 23, 2026