News for hackers. Stuff that matters.
Re:GPT-5.6 by ainch on Friday July 10, 2026 @02:22AM (#48856418)
Yann is a big SSL guy but I don't think he was involved in the original DINO - he's not listed as a co-author or anything.
Re:GPT-5.6 by vatsachak on Friday July 10, 2026 @09:35AM (#48859730)
DINO was created independent of JEPA but uses a similar principle of self supervised learning through minimizing the prediction error of a latent.

The difficulty in predicting a latent is so called "collapse"; the embedding neutral network can always output the zero vector and this would predict the output correctly.

There are different ways to solve this, DINO uses two different models - a teacher and a student and LeCunn uses an explicit term against collapsing to a single output.

Yann mentions DINO in his talks