Stars
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
[RA-L`2026] Active Kinematic Modelling for Precise Manipulation of Unseen Articulated Objects
A high-fidelity, general-purpose platform for embodied agent training and testing.
Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Character Animation Diffusion with Any Topology
[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
A vector-quantized periodic autoencoder (VQ-PAE) for motion alignment across different morphologies with no supervision [SIGGRAPH 2024]
Project Page for Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
Collect some related resources of NVIDIA Isaac Sim
Warp is the agentic development environment, built for coding with multiple AI agents.
Unified framework for robot learning built on NVIDIA Isaac Sim
Implementation of CrossLoco, currently lite version
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
Release for Improved Denoising Diffusion Probabilistic Models
Repository for our paper: FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning, Proceedings of the 12th International Conference on Learning Representations (ICLR)
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Model-based design and verification for robotics.
The course text for MIT 6.832 (and 6.832x on edX)
Reinforcement Learning Environments for Omniverse Isaac Gym
Accelerate "hjkl" moving. Also works in vscode-neovim.
Sample code shown during Developer Office Hour session for NVIDIA Omniverse.