Renping Zhou

World action models do not need to render clean future video to generalize: conditioning on a single forward pass of pure noise captures virtually all the robustness benefits of multi-step diffusion at a fraction of the compute.

MemoryVLA++ achieves up to 28% performance gains in robotic manipulation tasks by integrating memory and imagination, transforming how robots handle temporal dependencies.

Decoupling visual perception from motor control in robot learning yields a 27% performance boost and better generalization.