Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision

arXiv:2605.28865v1 Announce Type: new Abstract: What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random embodied exploration, we find that its latent space develops spatial semantic structure that mirrors physical geometry -- direction accuracy 0.677+-0.029 versus 0.547 for a randomly initialized encoder, and posit