Papers
1–4 of 4Statistical and structural identifiability in representation learning
Representation learning models exhibit a surprising stability in their internal representations. Whereas most prior work treats this stability as a single property, we formalize it as two distinct con...
Disentangled Representation Learning through Unsupervised Symmetry Group Discovery
Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentan...
Hypersolid: Emergent Vision Representations via Short-Range Repulsion
A recurring challenge in self-supervised learning is preventing representation collapse. Existing solutions typically rely on global regularization, such as maximizing distances, decorrelating dimensi...
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure rep...