JEPA Pointed Out as Similar to PMAX Concepts

SchmidhuberAI · x · 2026-07-18

This in-depth post discusses the relationship between LeCun's JEPA and Schmidhuber's team 1992 PMAX, with the core argument being: the key ideas behind JEPA are not new.

The author suggests that PMAX is essentially a method for two non-generative neural networks to learn latent representations through prediction/matching. They further point out that JEPA is highly similar to this concept, providing extensive references to support their claim.

Original post →

More from Research

Research channel →