jepa
4 free lessons tagged jepa across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
EBMs as a Unifying Lens
Why LeCun treats energy as the common language of machine learning. This lesson shows how classification, generative models, self-supervised learning, JEPA, and diffusion all read as energy-based models, ties the contrastive-versus-regularized split back to self-supervised learning, and gives an honest account of where explicit EBMs help and where they do not.
From I-JEPA to V-JEPA: World Models and Planning
The JEPA idea becomes concrete in I-JEPA on images and V-JEPA 2 on video. This lesson covers the multi-block masking that makes I-JEPA work, how an action-conditioned video model becomes a world model, and how predicting representations enables planning by model-predictive control instead of a fixed policy.
Inside a JEPA: Encoders, Predictors, and Collapse
Predicting a learned representation invites a trivial cheat: represent nothing. This lesson opens the JEPA machine, the context encoder, target encoder, and predictor, shows the training loop in code, explains why representation collapse is the central danger, and how asymmetry, stop-gradient, and an EMA target defeat it without negatives.
Why Predict Representations, Not Pixels
Self-supervised learning has three families: reconstruct the input, contrast augmented views, or predict in a learned embedding space. This lesson explains why the third, the joint-embedding predictive approach behind JEPA, sidesteps both wasted capacity on unpredictable pixels and hand-crafted augmentation biases.