AINeutralarXiv – CS AI · 10h ago5/10
🧠
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
Researchers propose Sub-JEPA, an improved approach to training world models that addresses stability issues in Joint-Embedding Predictive Architectures by applying Gaussian constraints across random subspaces rather than the full embedding space. The method achieves better performance than the existing LeWorldModel baseline while maintaining training stability and representation flexibility.