Training JEPA architectures requires designing cost functions that produce low energy on training data but high energy outside the training manifold; there are only two classes of methods for this: (1) contrastive methods push down energy on real data and push up energy on synthetic negative samples, but they don't scale well to high dimensions and require many negative samples; (2) regularized methods use regularizers to minimize the volume of low-energy space, which scales better.

factualpending

Speaker

Yann LeCun

Evidence Quote

“I only know two classes of methods for this one set of method is called contrastive...another set of method...called regularized method”

Source

The Shape of AI to Come! Yann LeCun at AI Action Summit 2025— DSAI by Dr. Osbert Tay
Created: 8/11/2026, 1:17:36 AM

Your notes

Loading notes...