NeurReps
NeurIPS 2026 Workshop · Sydney, Australia

Symmetry and Geometry in Neural Representations

A gathering of mathematicians, machine learning researchers, and neuroscientists working to uncover the geometric principles shared by brains and machines.

Fri Dec 11 – Sat Dec 12, 2026 Exact day TBA by NeurIPS Sydney, Australia

The fields of biological and artificial intelligence are 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, sparsity, equivariance, and compositionality are guiding the development of more generalizable and interpretable models.

NeurReps brings these threads together — fostering dialogue among machine learning researchers, neuroscientists, and mathematicians working to uncover unifying geometric principles of neural computation.

Just as geometry and symmetry once unified the models of twentieth-century physics, we believe they will now illuminate the computational foundations of intelligence.
Program

Invited Speakers

Five talks spanning the geometry of brain computation, mechanistic interpretability, and foundation models.

Team

Organizers

Team

Area Chairs

Area chairs for the 2026 edition are being finalized. Announcing soon
Submit

Call for Papers

Two tracks, one poster session — a subset of submissions will be selected for spotlight talks. Full details and deadlines coming soon.

9pages, excl. refs

Proceedings Track

Self-contained, highly-developed research papers. Archivally published in a dedicated PMLR volume.

4pages, excl. refs

Extended Abstract Track

Early-stage results, negative findings, opinion pieces, or novel datasets. Non-archival — may be posted to arXiv.

Support

Sponsors

Archive

Past Editions

A running history of NeurReps at NeurIPS — organizers, speakers, and proceedings from each year.