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 ...