-
NVIDIA Research
- Seattle, WA
- http://web.mit.edu/caelan/www/
- @caelangarrett
Starred repositories
Code for the paper "Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction" presented at CoRL 2024.
Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)
Unitree Go2, Unitree G1 support for Nvidia Isaac Lab (Isaac Gym / Isaac Sim)
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
Compares two latex files and marks up significant differences between them. Releases on www.ctan.org and mirrors
Open-source and strong foundation image recognition models.
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
[ICLR 2024] PyTorch Code for Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
Vision package for robot manipulation and learning research
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
PartNet 3D Web-based Shape Parts Annotation System
LLM3: Large Language Model-based Task and Motion Planning with Motion Failure Reasoning
Robot kinematics implemented in pytorch
Visualizing the DROID dataset using Rerun
Example URDF file external data loader plugin for Rerun
Visualize streams of multimodal data. Fast, easy to use, and simple to integrate. Built in Rust using egui.
Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"
Newton and Quasi-Newton optimization with PyTorch
a state-of-the-art-level open visual language model | 多模态预训练模型
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Implementation of the discrete Fréchet distance
The official Python library for the Google Gemini API
An open source implementation of CLIP.
Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]