Neon alley · fast pan right
First-person camera control in a neon-lit city.
INTERACTIVE WORLD MODELS · PROJECT PAGE
H3-World enables character and camera control across diverse visual environments.
♣ Research internship at Tencent · * Corresponding authors · ◆ Project Leader

Language becomes direct, visible control across characters, cameras, and environments.
First-person camera control in a neon-lit city.
First-person lateral movement in a complex cave environment.
Third-person navigation across an open desert scene.
Third-person camera motion in a detailed fantasy interior.
A world model should do more than recognize what is happening. It should understand what a person wants to happen next.
H3-World provides one language for character, viewpoint, motion, and environment, keeping directions connected instead of treating them as isolated effects.
H3-World learns language-aligned actions while preserving the generative prior of the world model.

Actions can change over time while the generated sequence remains visually coherent.

Language-aligned action conditioning steers motion without discarding scene content.

H3-World transfers control to unseen combinations of visual environments and actions.

If H3-World supports your work, cite the project.
@article{chen2026h3world,
title={H3-World: Turning Language Understanding into World Control},
author={Chen, Danze and Wang, Zeqing and Lin, Ziyue and Yang, Xingyi and Jin, Yeying},
year={2026}
}