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

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision arXiv:2605.28865v1 Announce Type: cross 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