@SungjinAhn_
๐ We introduce Neural Theorizer (NEO) โ a new type of world model that learns to theorize the world from observation, without language or LLM supervision. Selected as an ICML 2026 oral presentation โ 0.7% of submitted papers. The paper asks: "What does it mean to understand the world and build a world model?" Todayโs world models are often trained to predict the future: the next frame, next latent state, or next observation. But is prediction enough? We argue that a world model should be a theory-building system: one that discovers reusable primitives, composes them into executable explanations, and transfers those explanations to novel phenomena. NEO is our first step toward this vision โ a World Theory Model that learns explicit, compositional theories from raw observation. This work was led by my wonderful students: Doojin Baek*(@doojin_a_baek), Gyubin Lee* (@gyubin0521), Junyeob Baek (@JunyeobB), and Hosung Lee (@HosungLee_). For more details, take a look at the paper โ and if youโre attending ICML, letโs talk there! ๐ arXiv: https://t.co/TGMXLLfzP7 ๐ Project page: https://t.co/aLJywp8rfq