BoxWorld: Let World Engines Control and Video Generators Render
BoxWorld: Let World Engines Control and Video Generators Render
BoxWorld hands user-defined interaction rules to the Box World Engine, then has the Box-State generative renderer autoregressively render a real-time interactive video world from the object states. The paper says it clearly outperforms end-to-end world models on evaluations including PairedStateBench and remains competitive on several public benchmarks. Training has three stages: learning object localization and state transitions from automatically annotated open-domain and game videos, then rollout distillation on self-generated histories.
Separating interaction reasoning from generative rendering, and comparing it with end-to-end video world models, offers one way to divide the work in controllable game worlds.
Source: arXiv Game World Models & Generation · arxiv.org