Sign up to save your podcasts
Or
Share LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation
Audio overview of LeJEPA — how Balestriero and LeCun proved isotropic Gaussian embeddings are optimal and distilled it into a 50-line self-supervised method.
View all episodes
By Adrian WeddAudio overview of LeJEPA — how Balestriero and LeCun proved isotropic Gaussian embeddings are optimal and distilled it into a 50-line self-supervised method.