LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation
Balestriero and LeCun prove isotropic Gaussian embeddings are optimal, then build a 50-line self-supervised method eliminating stop-gradients and EMA teachers.
Tag: research
38 posts
38 posts
Balestriero and LeCun prove isotropic Gaussian embeddings are optimal, then build a 50-line self-supervised method eliminating stop-gradients and EMA teachers.
Single-agent safety does not compose in multi-agent systems. 1.5M interactions show 46.34% attack success rates and 16-minute median failure windows.