Social-JEPA: Emergent Geometric Isomorphism

arXiv:2603.02263v2 Announce Type: replace-cross Abstract: World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between th