RDT-1B is a 1B-parameter (largest to date) imitation learning Diffusion Transformer pre-trained on 1M+ (largest to date) multi-robot episodes. Given language instruction and RGB images of up to three ...
Abstract: Reconstructing computed tomography (CT) images from incomplete projection data poses a challenging ill-posed inverse problem. Existing unsupervised diffusion-based methods are typically ...
Diffusion policy exhibits promising multimodal property and distributional expressivity in robotic field, while not ready for real-time end-to-end autonomous driving in more dynamic and open-world ...
Abstract: Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results