AIBullisharXiv – CS AI · 7h ago6/10
🧠
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
Researchers introduce UR-JEPA, a novel regularization technique for Joint-Embedding Predictive Architectures that addresses representation collapse by targeting uniformly rectifiable measures rather than isotropic Gaussians. The method demonstrates superior performance on Inet10 with an 0.83 percentage-point gain over existing approaches and produces geometrically distinct embeddings with sharper spectral drops, suggesting more structured learned representations.