Yann LeCun’s JEPA Has Evolved. Here’s What It Can Do.

In this episode of Attention Span, we explore three recent JEPA papers and what they reveal about learning to predict, plan, and act: H-JEPA learns different levels of abstraction, connecting longer-range plans to the movements needed to carry them out. DeepJEPA learns when to spend extra computation refining a prediction, with more work concentrated around contact and interactions between objects. RoboJEPA scales predictors from 22 million to 8 billion parameters, drawing on experience from twelve robot embodiments and testing planning on a physical robot. Along the way, we explain embeddings