This project provides a framework for controlling robots in robot hardware and MuJoCo simulation through XR (VR/AR) input devices. It allows users to manipulate robot arms using natural hand movements ...
We train latent diffusion models, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through ...
Abstract: In the context of the big data era, the extensive penetration of the Internet and the rapid development of database technology have led to an explosive growth in the amount of data generated ...