Unified framework for robot learning built on NVIDIA Isaac Sim

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

机器人技术栈资料汇总

This is the basis of my PhD thesis - not particularly clean or polished

Simulation-based multiple shooting for dynamically retargeting contact-rich whole-body robot motions.

Ultra-fast and customizable Python charts

The open-source AI voice studio. Clone, dictate, create.

Depth Anything 3

Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).

Official code repository for "Uncertainty Quantification for Flow-Based Vision-Language-Action Models".

AirPods liberated from Apple's ecosystem.

PF: a header only template library for fast particle filtering!

Code and data repository for RGB-Dog CVPR 2020 paper

A feed-forward 3D foundation model for reconstructing scenes from streaming data

[Science Robotics 2026] Official Implementation of the paper RL-100

MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

High accuracy RAG for answering questions from scientific documents with citations

A Paper List for Humanoid Robot Learning.

Puffing up reinforcement learning

Flow Policy Gradients for Robot Control

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Free Motion Capture for Everyone 💀✨

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.