NeurIPS 2025
December 6th or 7th, 2025
San Diego, USA
The fields of biological and artificial intelligence are increasingly converging on a shared principle: the geometry and topology of real-world structure play a central role in building efficient, robust, and interpretable representations. In neuroscience, mounting evidence suggests that neural circuits encode task and environmental structure through low-dimensional manifolds, conserved symmetries, and structured transformations. In deep learning, principles such as sparsity, equivariance, and compositionality are guiding the development of more generalizable and interpretable models, including new approaches to foundation model distillation.
The NeurReps workshop brings these threads together, fostering dialogue among machine learning researchers, neuroscientists, and mathematicians to uncover unifying geometric principles of neural representation. Just as geometry and symmetry once unified the models of 20th-century physics, we believe they may now illuminate the computational foundations of intelligence. We aim to bring together researchers from applied mathematics and deep learning with neuroscientists whose work reveals the elegant implementation of mathematical structure in biological neural circuitry.
We are excited to announce our 4th annual NeurIPS workshop this December. This year’s workshop expands into emerging frontiers, including geometric mechanistic interpretability, geometry of representations in foundation models of brain activity, and improvements of LLM design guided by geometric understanding of transformers. Our past invited and contributed talks drew exciting connections between trends in geometric deep learning and neuroscience, emphasizing parallels between equivariant structures in brains and machines. This year's workshop will feature five invited talks covering emerging topics on the geometry underlying the brains computations, the role of topology in deep learning and the brain, how we can use insights from classic geometric deep learning to improve foundation models, the forefront in foundation models of the brain as well as how we can extract the brains computational structure with mechanistic interpretability, and, finally, the role of dynamics in shaping neural representations.
University of Fribourg
Francisco Acosta
UC Santa Barbara
Rishi Sonthalia (Boston University)
Thomas Gebhart (University of Minnesota)
Paxon Frady (Intel)
Maghesree Chakraborty (Intel)
Mustafa Hajij (UCSF)
Jacob Zavatone-Veth (Harvard)
Sjoerd van Steenkiste (Google)
Eric Qu (UC Berkeley)
Arjun Karuvally (UMass Amherst)
Alex Williams (NYU & Flatiron Institute)
Valentino Maiorca (Sapienza University & ISTA)
Bo Zhao (UCSD)
Jianke Yang (UCSD)
Brian Bell (Los Alamos National Lab)
Salvish Goomanee (CNRS)
Rana Muhammad Shahroz Khan (UNC Chapel Hill)
Charlie Godfrey (Thomson Reuters Labs)
Binxu Wang (Harvard)
Derek Lim (MIT)
Yanan Long (University of Chicago)
Manos Theodosis (Harvard)
Nikos Kanakaris (USC)
Adrish Dey (Boston University)
Abhinav Kumar (Michigan State University)
Dehong Xu (UCLA)
Qingsong Wang (University of Utah)
Aslan Satary Dizaji (AutocurriculaLab)
Johan Mathe (Atmo, Inc.)
Vinayak Abrol (IIT Delhi)
Kijung Yoon (Hanyang University)
Nirupama Tiwari (IISc Bangalore)
Arif Dönmez (IUF Leibniz)
Daniel Apraez (IIT, Genova)
Stephan Chalup (The University of Newcastle)
Marco Pegoraro (Sapienza University)
Sharvaree Vadgama (UvA)
Aishwarya Balwani (Georgia Tech)
Santiago Velasco-Forero (Mines Paris)
Julian Suk (University of Twente)
Emanuele Rodola’ (Sapienza University)
Shreya Kapoor (FAU Erlangen-Nüremberg)
Yu Tian (Nordita)
Tao Hu (LMU)
Tomas Karella (Czech Academy of Sciences)
Tobias Cheung (University of Edinburgh)
Marco Piangerelli (Camerino University)
Irene Cannistraci (Sapienza University)
Maksim Zhdanov (UvA)
Paul Samuel Ignacio (University of the Philippines Baguio)
Daniel Platt (Imperial College)
Dongmian Zou (Duke Kunshan University)
Wolfgang Polonik (UC Davis)
Alpha Renner (Forschungszentrum Jülich)
Behrooz Tahmasebi (MIT)
Yu (Demi) Qin (Tulane University)
Wenhao Zhang (UT Southwestern)
Samuele Papa (UvA)
Congyue Deng (Stanford)
Jinen Setpal (DagsHub)
Ruqi Zhang (Purdue University)
Ruchira Dhar (University of Copenhagen)
Jens Agerberg (KTH)
Vasco Portilheiro (UCL)
Barbaresco Frédéric (THALES)