🛰️ Daily AI Frontier
‹ back to 2026-09-10

Programmable World Model

arXiv cs.CV Multimodal & Generative Zheng-Hui Huang, Guixu Lin, Jiacheng Lin, Yi-Chuan Huang, Ruihan Yu, Muyao Niu, Siqi Yang, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang 2026-09-09
Representative image for Programmable World Model

TL;DR - Programmable World Model separates explicit world-state evolution from video generation, enabling persistent entities and programmable rules in long-running interactive environments. This architecture supports playable games with coherent mechanics while using a pretrained video model as the visual renderer.

  • An agent converts natural-language instructions into executable entity states and transition rules.
  • A lightweight engine maintains persistent global state, including off-screen entities and non-visual attributes.
  • State-augmented 3D oriented bounding boxes and camera trajectories are compiled into conditioning signals for video generation.
  • On CombatStateBench, the method achieves 94% Count Accuracy and 98% State Accuracy, outperforming existing interactive video world models.

view merged work →