Junta Wu

Decoupling structured semantics from frame-level actions and distilling autoregressive rollouts via shared, compressed memory tokens solves the long-standing trade-off between real-time responsiveness and multi-step drift in interactive world models.

Imagine creating high-fidelity, navigable 3D worlds from just a text prompt or a single image – HY-World 2.0 makes it a reality.

Generate multi-view consistent videos with precise camera control and reconstruct high-quality 3D scenes from them, all without joint training.