yankai Xiang

seen2scene. [ ECCV 2026 ] Seen2Scene takes an incomplete real-world 3D scan and generates a complete, coherent 3D scene using visibility-guided flow matching — trained directly on real-world data.

HumanoidArena. Official repo of HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning

StereoDiffusion. Implementation of StereoDiffusion

PMT. Official implementation of Perceptive Behavior Foundation Model

motion_imitation. Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"

open_2DOF_robot_head. Open-source 2-DOF robot head designs for research use across various robotic platforms. Modular, extensible, and regularly updated.

Articulat3D. Official repository for the ECCV 2026 paper "Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints".

wococo. Python

rah. Shell

sru-pytorch-spatial-learning. Spatially-Enhanced Recurrent Units (SRU) - PyTorch Implementation

mjlab_playground. A collection of tasks built on mjlab

LivePingPong. TypeScript

CRISP-Real2Sim. (ICLR 2026) CRISP

academic-research-skills. Academic Research Skills for Claude Code: research → write → review → revise → finalize

human-humanoid-tools. Python

Fast-FoundationStereo. [CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

smp. Python

humanize. From Automated Idea Factory to Realization

web-access. 给 Claude Code 装上完整联网能力的 skill：三层通道调度 + 浏览器 CDP + 并行分治

SHTUCodeProxy. 上海科技大学校内 GenAI API 接入 Claude Code 和Codex的 Windows 及Linux图形化本地代理工具。

AMP_mjlab. Python

GenAI2OpenAI. 将学校的GenAI服务转为openai兼容格式，以适配下游任务，免去正式申请APIkey

webclash. Running clash on your headless machines!

claude-code-router. One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

GenAI2OpenAI. 将学校的GenAI服务转为openai兼容格式，以适配下游任务，免去正式申请APIkey

Structure-Sensor-Record. 📱 An iOS app for capturing RGB-D data directly using Structure Sensor. Built upon the official Structure SDK Viewer sample, tailored for streamlined RGB-D recording on iOS devices.

ClaudeTeam. Build an agent team with a single prompt, integrate with Lark (Feishu). Support Codex, Claude Code, Openclaw, and many other CLIs.

awesome-webgl. A curated list of awesome WebGL libraries, resources and much more

oh-my-codex. OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

mink. Python inverse kinematics based on MuJoCo.

mjviser. Web-based MuJoCo viewer powered by Viser

omniretargeting. Python

kimodo. Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

mujoco_learning. Jupyter Notebook

LATENT. Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

CLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

HumanoidSoccer. Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework

InstinctMJ. mjlab-native port of InstinctLab for humanoid RL and Project-Instinct workflows.

humanoid_skateboarding. [RSS 2026] "HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control"

pm-skills. PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

mujoco_menagerie. A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

BeautifulPointCloud. Transform your point cloud data into beautifully rendered 3D images.

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

direct_lidar_inertial_odometry. [IEEE ICRA'23] A new lightweight LiDAR-inertial odometry algorithm with a novel coarse-to-fine approach in constructing continuous-time trajectories for precise motion correction.

SuperOdom. A highly robust and accurate LiDAR-only, LiDAR-inertial odometry

amp_go2. AMP implementation for go2 edu

cosmos-policy. Cosmos Policy

elevation_mapping_cupy. Elevation Mapping on GPU.

InstinctLab. Python

stepit. A flexible framework for connecting legged robots, input devices, and control algorithms.

robotic_world_model_lite. Lightweight implementation of Robotic World Model (RWM) and Uncertainty-Aware Robotic World Model (RWM-U)

robot-motion-editor. A web-based tool that edits the robot motion file in instinctlab ecosystem

Anymal_Navigation. Extend the navigation capabilities of Anymal-C in IsaacLab using Deep Reinforcement Learning

LocoLab. IsaacLab rl locomotion env benchmark with sim2real robustness guarantees.

robotic_world_model. 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 Reinforcement Learning Work on Real Robots

HoloAgent. A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localization, and autonomous mobility and manipulation, with intelligent interaction with users.

Helpful-Doggybot. Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models

SPI-Active. Official Implementation of "Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning"

mjlab. Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

instinct_onboard. Onboard code for Project Instinct

FAST_LIO_LOCALIZATION. A simple localization framework that can re-localize in built maps based on FAST-LIO.

REASAN. Fully modularized learning framework for legged reactive navigation

COMPASS. Cross-embOdiment Mobility Policy via ResiduAl RL and Skill Synthesis

himloco_lab. train, export, and deploy HimLoco policies in the Isaac Lab environment

osmAG-LLM. Python

SAGE-3D_Official. This is the official repository of the paper "Towards Physically Executable 3D Gaussian for Embodied Navigation".

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

pace-sim2real. PACE: A systematic approach for sim-to-real transfer of legged robots, identifying actuator and joint dynamics with standard joint encoders.

InternNav-deploy. Edge deployment guide for InternNav-based perception and navigation on Unitree Go2 / Go2W / B2 robots (ROS 2, RealSense, Python).

URDF-Studio. URDF-Studio is a web-based visual URDF robot modeler with 3D workspace, structured skeleton/detail/hardware workflows, motor library integration, MuJoCo export, and AI assistance.

wasabi. Repository for our paper: Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations Proceedings of the 6th Conference on Robot Learning (CoRL),

PBHC. Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills"

beyondAMP. beyondAMP provides a unified pipeline to integrate Adversarial Motion Priors (AMP) into any IsaacLab robot setup, with minimal modifications and full compatibility with custom robot designs.

ddt_rl_isaacgym. Isaac Gym Environments for Legged Robots

CAPO-LeggedRobotOdometry. C++

InternUtopia. A simulation platform for versatile Embodied AI research and developments.

crocoddyl. Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

OmniPerception. Python

NaVILA-Bench. Vision-Language Navigation Benchmark in Isaac Lab

gauss_gym. Python

SRGS. The first to focus on HRNVS of 3DGS

InternNav. InternRobotics' open platform for building generalized navigation foundation models.

My_unitree_go2_gym. Python

visualize_uav_trajectory. Visualize the trajectory of the drone in the video

unitree_ws. C++

Go2Arm_Lab. A legged manipulator framework based on IsaacLab

go2w_sim2sim. Makefile

GMR. [ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

trackerLab. TrackerLab is a cutting-edge modular framework for humanoid motion retargeting, trajectory tracking, and skill-level control, built on top of IsaacLab.

rl_sar. Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

cusrl. Customizable Reinforcement Learning

HoST. [RSS 2025 Best Systems Paper Finalist] 💐Official implementation of "Learning Humanoid Standing-up Control across Diverse Postures"

engineai_legged_gym. Python

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

Wheel_legged_gym. Python

tita_rl. Official support TITA Reinforcement Learning repo

Awesome_Quadrupedal_Robots. Awesome Quadrupedal Robots

robot_lab. RL Extension Library for Robots, Based on IsaacLab.

bipedal-robot-learning-collection. Collection of high-quality robo learning papers for bipedal robots.

legged_control. NMPC, WBC, state estimation, and sim2real framework for legged robots based on OCS2 and ros-controls

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

DRL-Pytorch. Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

rsl_rl. A fast and simple implementation of learning algorithms for robotics.

ManiSkill. Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

Awesome-Robotics-Manipulation. A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

academic-website-template. Static web template for academics/research groups

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

hugo-theme-academic-cv. 🎓 Academic portfolio that boosts citations. AI generates pages, you own as Markdown. BibTeX auto-import, Jupyter, LaTeX, slides, visual block editor — free to host forever. 学术主页，AI 生成，Markdown 拥有 👇

DeepRL. Deep Reinforcement Learning Lab, a platform designed to make DRL technology and fun for everyone

Embodied_AI_Paper_List. [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

Tinker. This project features an open-source small bipedal robot designed for research, education, and hobbyist experimentation.

Notes. Yunhao Cao's Opensourced Study Notes

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

LocomotionWithNP3O. unitree Go2 robot learns locomotion with N-P3O algorithm and HIM alike policy trained by isaacgym

pinocchio. A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

Book-Mathematical-Foundation-of-Reinforcement-Learning. This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

drl-zh. Deep Reinforcement Learning: Zero to Hero!

arm_controllers. A collection of controllers

ML_DL_CV_with_pytorch. 一个计算机视觉、机器学习与深度学习相关的项目，看课程的笔记还有自己做的程序

CSBasicKnowledge. This repo will record some knowledge about computer science, artificial intelligence and EE

TinyMPC. Model-predictive control for microcontrollers, ICRA 2024 Best Paper Award

CSSummerCamp2024. 2024年计算机保研夏令营&冬令营通知

ProgrammingVTuberLogos. High-quality PNGs for logos I made for fun

zjut-icicles. 浙江工业大学课程攻略共享计划

awesome-avalonia. A collection of interesting libraries and tools for Avalonia project.

KDRobot_RM2023Sentry_Navigation. C++

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

APRL. Efficient Real-World RL for Legged Locomotion via Adaptive Policy Regularization

Shenzhen_innoX_2024wc_FishChassis. Embedded system of the Chassis. Shenzhen innoX 2024 winter robotic camp for high school students.

HPM5361MiniFOC. C

image2display. 跨平台的现代图片/字体取模软件。Cross platform GUI converting images or fonts into array data.

Avalonia.Samples. Avalonia.Samples aims to provide some minimal samples focusing on a particular issue at a time. This should help getting new users started.

GY-H1. An ICM42688 IMU With CAN Interface

dgm. An open source high-performance FOC motor driver

LLVM-embedded-toolchain-for-Arm. A project dedicated to building LLVM toolchain for Arm and AArch64 embedded targets.

ArduinoMenu. Arduino generic menu/interactivity system

Awesome-Embeded-AI. 收集关于嵌入式领域的机器学习算法实现的进展、相关论文和文章、开发库等，帮助初学者快速了解、学习和入门嵌入式领域的机器学习。CC-BY-NC-SA 4.0。

visp. Open Source Visual Servoing Platform

Enterprise_E. 第十六届智能车竞赛-国家级一等奖-嵌入式控制开源(恩智浦杯/飞思卡尔杯)-全国第14名 🏆

Balance_On_Wheels. Modeling and Control of Two-Legged Wheeled Robot: In this project, we will be building a two wheeled robot (with a hip and knee joint) which can balance at variable heights including a provision for jumping.

RM2010_AGVinfantry. RM2021舵轮步兵电控开源

StreeingInfantry-TDT. C

Inverted_Pendulum_DengFOC. 基于SimpleFOC官方开源的动量轮倒立摆项目，低成本化和小型化后应用在DengFOC上

serial-lan-debug-software. 基于C#设计了一款上位机软件（windows）。该上位机软件使用 自制协议，实现与下位机的多功能交互。软件支持串口、TCP、UDP 通信，能够实现毫 秒级的精准定时发送，支持 ASCII 字符、HEX 格式的文本显示；支持自制协议数据格 式的波形动态显示、存储且不限制缓存上限，显示波形能够自由缩放、移动以及数据标 签提示；支持对下位机的参数进行调试同时可以从下位机导入调试参数列表，且能够在 调试的过程中接收下位机反馈数据并显示数据波形；支持自制协议图片格式的图片接收 和图片文件夹导入、存储，能够缓存所有图片并随时访问，集成一定图像处理算法并能 够同时显示处理前、后的图片，支持编译外部算法并能在软件中查看编译、调试信息。

Fusion. C

stable-diffusion. A latent text-to-image diffusion model

stable-diffusion-webui. Stable Diffusion web UI

go-ringbuffer. A simple thread-safe ring buffer without Mutex lock.Optimize for huge buffers.

yolov7. Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

IceWallet. A very simple Personal Finance App

rt-thread. RT-Thread is an open source IoT Real-Time Operating System (RTOS). https://rt-thread.github.io/rt-thread/

Awesome-Embedded. A curated list of awesome embedded programming.

upm. UPM is a high level repository that provides software drivers for a wide variety of commonly used sensors and actuators. These software drivers interact with the underlying hardware platform through calls to MRAA APIs.

Learning-OpenCV-3_examples. C++

coreutils. Enhancements to the GNU coreutils (especiall head)

cJSON. Ultralightweight JSON parser in ANSI C

C. Collection of various algorithms in mathematics, machine learning, computer science, physics, etc implemented in C for educational purposes.

clion-custom-defined-compiler-examples. Set of examples how to use CLion with various unsupported compilers using Custom Defined Compiler feature

fann-on-mcu. C

auto-sklearn. Automated Machine Learning with scikit-learn

Qt-Creator-Darcula. Darcula color scheme for Qt Creator GUI and syntax highlighting theme

CS-Awesome-Courses. 计算机的优秀课程

EnergyStar. A terrible application setting SV2 Efficiency Mode for inactive Windows apps and user background apps

yolov5. Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

CleanMyWechat. 自动删除 Windows 和 Mac 电脑端微信缓存数据，包括从所有聊天中自动下载的大量文件、视频、图片等数据内容，解放你的空间。

bl706_dk. BL706 Develop Kit 开发板资料

PyBot. ATRI是一只基于word2vec指令匹配，用seq2seq聊天的，以及对接多方NLP平台智能ai聊天机器人

free-font. 大概是2020年最全的免费可商用字体，这里收录的商免字体都能找到明确的授权出处，可以放心使用，持续更新中...

WeJH-Taro. Taro + Vue3 微精弘小程序前端

LangZhongPomodoro. 为B站up主@铁打的郎中开发的一款番茄时钟小程序

evoBasic-lang. modern BASIC programming language

PAT-Advanced-Level. Solutions to PAT💯

zju-icicles. 浙江大学课程攻略共享计划

HDB3_FPGA. HDB3 decode and endecode by Verilog HDL

FastSQLQueue. A Simple MySQL Queue for Golang

Video-background-page. 模仿墨迹天气首页，利用视频作为网页背景。

fast-xml-parser. Validate XML, Parse XML and Build XML rapidly without C/C++ based libraries and no callback.

learning-materials. 学习资料

walk-view. 2021 代的精弘毅行前端，采用了 Vue3 + Naive UI

ricq. Rust 高性能 QQ 协议（原RS-QQ）。Linux-musl运行内存1.6MB。

NXP_12th_BalanceCar. 2017 年第十二届全国大学生“恩智浦”杯智能汽车竞赛全国一等奖 - 匿名队伍

freescalesmartcar. 飞思卡尔智能车竞赛源代码(含记忆算法)

smartCar. 飞思卡尔智能车程序

notes-linear-algebra. 线性代数笔记

feed-netkeeper. Openwrt闪讯插件

CTF-RSA. 总结一下各路大师傅的RSA脚本233

Scope. 2020 数媒创新实践，基于 React.js + AR.js + tensorflow.js 打造跨平台的 AR 识图交互应用 web 站点

info-server-2021. ZJUT新生学号查询系统后端 2021

swot. Identify email addresses or domains names that belong to colleges or universities. Help automate the process of approving or rejecting academic discounts.

onebot. OneBot：统一的聊天机器人应用接口标准

LibSpritesGUI_12864. 能够运行在单片机上的多图层128*64精灵图2D引擎系统

go. The Go programming language

mirai-console. mirai 的高效率 QQ 机器人控制台

Github_Friends. Github_Friends

MinecraftDeveloperGuide. 📝Minecraft developer Chinese guide，我的世界开发者中文指南

Huorong_Vulnerabilities. Huorong Internet Security vulnerabilities 火绒安全软件漏洞

reactos. A free Windows-compatible Operating System

TabNine. AI Code Completions