News Center

location: Home > News Center > News > Content

AIR Research | ODEWorld: A Continuous-Time Embodied World Model for Efficient Generation, Arbitrary Frame Interpolation and Backward Rollout

Source:       Time:2026-08-05
Current visual world models treat robot manipulation as a stack of discrete frames — frame 1, frame 2, frame 3 — predicting each next instant and rolling forward step by step. But physical motion happens between snapshots, not at them. Working with UC Berkeley's BAIR group, AIR proposes ODEWorld, a continuous-time embodied world model that learns the direction and speed at which the world changes in physical time, rather than solving a frame-by-frame "what comes next" fill-in-the-blank. The approach enables efficient generation, arbitrary frame interpolation between any two moments, and even backward rollout from a future state.

https://air.tsinghua.edu.cn/info/1007/2535.htm



上一条:AIR Research | MakoXC: Turning AI Compute Loose on Electronic Structure 下一条:AIR People | Exploring the Next Generation of AI: Professor Hang Li Joins AIR

【关闭】

Relevant news

Email:Airoffice@air.tsinghua.edu.cn
Tel:(010)82151160

Address:12 / F, block C, Qidi science and technology building, Tsinghua Science and Technology Park, Haidian District, Beijing

wechat

Jing ICP Bei No. 15006448 | all rights reserved@ Institute of intelligent industry, Tsinghua University