Rui-Cheng Wang

OctWorld achieves unprecedented long-range video generation with spatial consistency, outperforming traditional methods by leveraging an innovative 3D memory architecture.

Achieving dense metric depth completion from sparse dToF sensors, our framework outperforms state-of-the-art methods while being trained solely on synthetic data.

Force-based memory enables VLA models to achieve over 80% success in complex manipulation tasks, outperforming traditional memory methods with minimal computational cost.