Code Plans, Diffusion Renders: Open-Ended Generative World Modeling

The paper introduces CoDeR, a new paradigm for world modeling that explicitly builds an executable world using code rather than relying solely on visual observations. CoDeR translates high‑level concepts into structured world rules, executable dynamics, and perceptual observations through five complementary roles, enabling long‑term memory, open‑ended interactions, autonomous world evolution, and persistent multi‑agent dynamics. Experiments show that this framework extends the capabilities of existing world models and achieves state‑of‑the‑art performance across multiple evaluation settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• agents
• diffusion
• benchmarks