Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models

arXiv:2605.09241v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural constraints,...