LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
Big data , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2roles
background 1polarities
background 1representative citing papers
MCBP detects boundaries by computing discrete mean curvature from k-nearest neighbor patches on the data manifold, then decomposes data into low-curvature smooth and high-curvature boundary subsets to improve clustering.
citing papers explorer
-
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
-
A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
MCBP detects boundaries by computing discrete mean curvature from k-nearest neighbor patches on the data manifold, then decomposes data into low-curvature smooth and high-curvature boundary subsets to improve clustering.