Home / AI Research / Code World Model 2.0: Towards Infinite Controllable Video Generation
COAI Research
Code World Model 2.0: Towards Infinite Controllable Video Generation
by inclusionAI · Ruoyu Wang, Hao Zhong, Yanming Yang, Jiahao Tian, Lin Liu, Biao Gong
Visual proxies decouple explicit world-state simulation from photorealistic video synthesis, offering a controllable interface for both offline clip creation and real-time interactive streaming. Yet a practical renderer must address two challenges. Upstream proxies vary from coarse layouts to fine articulated geometry depending on the interaction, and streaming inference must operate in a few causal steps without accumulating drift across self-generated history. We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language. Trained on an aligned…
Upvotes20
Comments2
Published16 Nov 2026
More from inclusionAI
| LILing 3.1 FlashAI Model APIs · #53 | $0.060 / $0.18 |
| LILing 3.0 Flash VLAI Model APIs · #90 | $0.060 / $0.18 |
| LILing 3.0 TinyAI Model APIs · #123 | $0.015 / $0.045 |
| LILing 3.0 FlashAI Model APIs · #130 | $0.021 / $0.063 |
| INinvoker-render-1.0AI Models · #3657 | 53.6K |