Official repository for the paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe"

LGGD: Language-Guided Grasp Detection with Coarse-to-Fine Learning for Robotic Manipulation

Welcome to SIMPLE, a full-stack simulation environment for humanoid loco-manipulation, built on AMO/SONIC, with integrated support for mainstream VLAs such as Psi-0, Pi05, GR00T, and more.

RL_Training Repo Based on Isaaclab

Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforceme…

Publication-ready NN-architecture schematics.

Latex code for making neural networks diagrams

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

PaperBanana: Automating Academic Illustration For AI Scientists

Code for our ICRA 2024 paper on learning diverse skills

Repository for our paper: Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions. (ICRA 2023)

HORT: Monocular Hand-held Objects Reconstruction with Transformers, ICCV 2025

A general physic-based retargeting framework.

A group project implementing deep learning models (CNN, ResNet50, BiLSTM) for video-based anomaly detection. The pipeline includes preprocessing, custom CNN baselines, transfer learning, and tempor…

HORT: Monocular Hand-held Objects Reconstruction with Transformers, ICCV 2025

[3DV 2026] Official implementation of FollowMyHold

GRAB: A Dataset of Whole-Body Human Grasping of Objects

ROS2 version of FAST_LIO2. Welcome to the technical communication discord server discord: https://discord.gg/U3B65MGH8m

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

A computationally efficient and robust LiDAR-inertial odometry (LIO) package

SAM 3D Objects

MANO hand model in PyTorch (anatomy consistent, anchors, etc)

Builder and index for PyTorch packages

Various retargeting optimizers to translate human hand motion to robot hand motion.

[ICLR 2025] Cross-Embodiment Dexterous Grasping with Reinforcement Learning

Code for [AAAI 2026] AffordDex: Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors