A recurring challenge in self-supervised learning is preventing representation collapse. Existing solutions typically rely on global regularization, such as maximizing distances, decorrelating dimensions or enforcing certain distributions. We instead reinterpret representation learning as a discrete packing problem, where preserving information simplifies to maintaining injectivity. We operationalize this in Hypersolid, a method using short-range hard-ball repulsion to prevent local collisions. This constraint results in a high-separation geometric regime that preserves augmentation diversity, excelling on fine-grained and low-resolution classification tasks.
@article{arxiv.2601.21255,
title = {Hypersolid: Emergent Vision Representations via Short-Range Repulsion},
author = {Esteban Rodríguez-Betancourt and Edgar Casasola-Murillo},
journal= {arXiv preprint arXiv:2601.21255},
year = {2026}
}