AINeutralarXiv – CS AI · 14h ago6/10
🧠
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
Researchers demonstrate that VAE-based world models develop organized spatial semantic representations through physical exploration alone, without linguistic input. The geometric structure of the physical world emerges as the primary organizing principle, with prediction performance and semantic alignment improving together across training, suggesting a shared underlying mechanism.