arXiv Game World Models & Generation· Shaoyang Guo·· 2026-09-30PickAI score45
Why conventional world models fail to learn cellular automata
Why Do Conventional World Models Fail to Learn Cellular Automata?
AI summary
An arXiv paper uses cellular automata to test conventional world models and finds that although they predict most pixels, they rarely complete a full rollout: a CNN predicts 96.3% of cells correctly but completes only 18.9% of rollouts, and a joint diffusion model completes none.
Why it matters
The paper breaks down three failure modes of world models and offers a fix for each that only changes the information flow, serving as a reference for debugging long-horizon rollouts.
Source: arXiv Game World Models & Generation · arxiv.org