Abstract: Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both ...
Abstract: Dynamic objects diversify the distribution of point cloud in the map, degrading the performance of the robotic downstream tasks. To address this problem, we present a novel real-time dynamic ...
This repository contains the implementation of HD-MoE, a hybrid and dynamic parallelism framework designed to optimize Mixture-of-Experts (MoE) Large Language Model (LLM) inference on 3D Near-Memory ...
This is the official code for the paper "DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models". Otherwise, you can use open-source image-to-video models such as ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results