YuMo Shu

quant-for-beginners. Jupyter Notebook

rclone. "rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

gen2act. Python

3x-ui. Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto)

cc-switch-cli. ⭐️ A cross-platform CLI All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

RoboDojo. RoboDojo Official Repo

cc-switch. A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

skills. Public repository for Agent Skills

LandPPT. 一个基于LLM的演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型，提供丰富的模板和样式选择，让用户能够创建高质量的演示文稿。

SSR-V2ray-Trojan. 2026机场推荐与机场评测

biliup. 自动直播录制、投稿、twitch、ytb频道搬运工具。命令行投稿(B站)和视频下载工具，提供多种登录方式，支持多p。

bilibili-cli. A CLI for Bilibili — browse videos, users, search, and feeds from the terminal

galbot_one_golf_description. Python

flux2. Official inference repo for FLUX.2 models

flux. Official inference repo for FLUX.1 models

ImageWAM. ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

academic-figure-generator. AI 驱动的学术论文配图生成平台。上传论文 → AI 分析内容生成 Prompt → 一键生成高质量科研配图，还有配套的skill可在主流agent中使用

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

pdfrip. A multi-threaded PDF password cracking utility equipped with commonly encountered password format builders and dictionary attacks.

mihomo. A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

cli. The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.

taehv. Tiny AutoEncoder for Hunyuan Video (and other video models)

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

BEHAVIOR-1K. BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

InternDataEngine. InternDataEngine: Pioneering High-Fidelity Synthetic Data Generator for Robotic Manipulation

DeepSeek-OCR. Contexts Optical Compression

clashfree. clash节点、免费clash节点、免费节点、免费梯子、clash科学上网、clash翻墙、clash订阅链接、clash for Windows、clash教程、免费公益节点、最新clash免费节点订阅地址、clash免费节点每日更新

RoboCOIN. RoboCoin + LeRobot integration

ProcVLM. ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation https://procvlm.github.io/

FastVideo. A unified inference and post-training framework for accelerated video generation.

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

AudioVisual. 仓库已停止维护

codex-loop-plugin. Claude Code-style recurring loop scheduling for OpenAI Codex.

codex. Lightweight coding agent that runs in your terminal

RoboLab. Python

voice-input-src.

sub2api. Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

AlphaBrain. The Comprehensive Toolkit for Embodied AI Models

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

polaris. A real2sim evaluation framework for generalist policies

best-igl-wiki. HTML

codex-cli-best-practice. from vibe coding to agentic engineering - practice makes codex perfect

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

claude-code-best-practice. from vibe coding to agentic engineering - practice makes claude perfect

Apollo-11. Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

tailscale. The easiest, most secure way to use WireGuard and 2FA.

opencv. Open Source Computer Vision Library

mink. Python inverse kinematics based on MuJoCo.

any4lerobot. 🎁 A collection of utilities for LeRobot.

tarsier. Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

jobs. A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development tool for exploring BLS data visually.

pixi. Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.

Causal-Forcing. [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

leonidk.github.io. a fork of https://jonbarron.info/ for use in jekyll builds with markdown page updates

lingbot-world. Advancing Open-source World Models

cursor-deepseek. A high-performance HTTP/2-enabled proxy server designed specifically to enable Cursor IDE's Composer to use DeepSeek's and OpenRouter's language models. This proxy translates OpenAI-compatible API requests to DeepSeek/OpenRouter API format, allowing Cursor's Composer and other OpenAI API-compatible tools to seamlessly work with these models.

new-api. A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥

das-datakit. Python

FinRL. FinRL®: Financial Reinforcement Learning. 🔥

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

jepa. PyTorch code and models for V-JEPA self-supervised learning from video.

ItChat. A complete and graceful API for Wechat. 微信个人号接口、微信机器人及命令行微信，三十行即可自定义个人号机器人。

wechaty. Conversational RPA SDK for Chatbot Makers. Join our Discord: https://discord.gg/7q8NBZbQzt

LDA-1B. [RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Action100M. A Large-scale Video Action Dataset

rcm. rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

redis. For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

GaVS. [SIGGRAPH 2025] Official Repo for Paper - GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

dreamzero. Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

dacite. Simple creation of data classes from dictionaries.

fourier-feature-networks. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

PyAV. Pythonic bindings for FFmpeg's libraries.

frankx. High-Level Motion Library for Collaborative Robots

lingbot-vla. A Pragmatic VLA Foundation Model

decord. An efficient video loader for deep learning with smart shuffling that's super easy to digest

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

LTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

docker-install. Docker installation script

DiffSynth-Studio. Enjoy the magic of Diffusion models!

Video-As-Prompt. [ICLR 2026] Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"

LightX2V. Lightweight Image Video Action Generation Inference Framework

mobile_manipulation_papers. Papers in Mobile Manipulation (Personal Collection)

sam-3d-objects. SAM 3D Objects

Awesome-Video-Robotic-Papers. This repository compiles a list of papers related to the application of video technology in the field of robotics! Star⭐ the repo and follow me if you like what you see🤩.

openai-cookbook. Examples and guides for using the OpenAI API

polydown. Batch downloader for polyhaven.com. Download 'HDRIs, Textures and Models' in any sizes with preview images from Poly Haven.

cursor-memory-bank. A modular, documentation-driven framework using Cursor custom modes (VAN, PLAN, CREATIVE, IMPLEMENT) to provide persistent memory and guide AI through a structured development workflow with visual process maps.

genie_sim. Simulation Platform from AgiBot

hexo. A fast, simple & powerful blog framework, powered by Node.js.

curobo. CUDA Accelerated Robot Library

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

molmo. Code for the Molmo Vision-Language Model

molmo2. Code for the Molmo2 Vision-Language Model

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

rerun. Visualize, query, and stream to train on multimodal robotics data.

diffusion_policy. [RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

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

large-video-planner. Python

acad-homepage.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

VMwareWorkstation. 手动上传官网的VMwareWorkstation安装包

TurboDiffusion. TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

ninja. a small build system with a focus on speed

PyFleX. Customized Python APIs for NVIDIA FleX

datasets. TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

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

ManiSkill-WidowX250S.

URDF. URDF file of A1 ,R1.

sim-evals. A simulation evaluation platform for DROID

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

miniball. Fast computation of the smallest enclosing ball of a point set, in low or moderately high dimensions.

DanceGRPO. An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

EmbodiedGen. Towards a Generative 3D World Engine for Embodied Intelligence

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

giga-world-0. GigaWorld-0: World Models as Data Engine to Empower Embodied AI

Pointcept. Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

Ctrl-World. ICLR 2026 Paper: Ctrl-World

giga-train. GigaTrain: An Efficient and Scalable Training Framework for AI Models

CoACD. [SIGGRAPH2022] Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search

awesome-video-generation. A collection of awesome video generation studies.

co-tracker. CoTracker is a model for tracking any point (pixel) on a video.

dexbotic. Dexbotic: Open-Source Vision-Language-Action Toolbox

daam. Diffusion attentive attribution maps for interpreting Stable Diffusion.

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

Infinity. [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

deskflow. Share a single keyboard and mouse between multiple computers.

TrendRadar. ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

Emu3.5. Native Multimodal Models are World Learners

robotics_arXiv_daily. Fetching Embodied AI Paper from ArXiv automatically

embodied-ai-start. [PKU EPIC Lab] 面向小白的具身智能入门指南

my_arXiv_daily. Python

debugpy. An implementation of the Debug Adapter Protocol for Python

frame-guidance. [ICLR 2026] Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

nope. [CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image

Any6D. [CVPR 2025] Any6D: Model-free 6D Pose Estimation of Novel Objects

Awesome6DPoseEstimation. Python

FoundationPose. [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

panda3d. Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU

bokeh. Interactive Data Visualization in the browser, from Python

megapose6d. Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

3DObjectTracking. Algorithms and Publications on 3D Object Tracking

SyncthingWindowsSetup. Syncthing Windows Setup

ReCamMaster. [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

dexmimicgen. This code corresponds to simulation environments used as part of the DexMimicGen project.

open_x_embodiment. Jupyter Notebook

gdown. Google Drive public file downloader when curl/wget fails.

hamer. HaMeR: Reconstructing Hands in 3D with Transformers

cosmos-transfer1-diffusion-renderer. Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

franka_description. Official models of Franka Robotics GmbH robots

Holistic-Robot-Pose-Estimation. [ECCV 2024] PyTorch implementation of "Real-time Holistic Robot Pose Estimation with Unknown States"

RoboPEPP. Python

DREAM. DREAM: Deep Robot-to-Camera Extrinsics for Articulated Manipulators (ICRA 2020)

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

GR00T-Dreams. DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

Cache4Diffusion. Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.

reloadium. Hot Reloading and Profiling for Python

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

HOGformer. Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration

pytorch-differentiable-histogram. PyTorch implementation for differentiable histogram

HOG-PyTorch. Batched Histogram of oriented gradients using PyTorch

PhysTwin. [ICCV 2025] PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

LuisaCompute. High-Performance Rendering Framework on Stream Architectures

LuisaRender. High-Performance Cross-Platform Monte Carlo Renderer Based on LuisaCompute

MDL-SDK. NVIDIA Material Definition Language SDK

FlashGS. C++

random-fourier-features-pytorch. Implementation of "Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains" by Tancik et al.

drrobot. Code for "Differentiable Robot Rendering" (CoRL 2024)

moviepy. Video editing with Python

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

diff-gaussian-rasterization. Cuda

cosmos-transfer1. Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

wgpu-3dgs-viewer. A 3D Gaussian Splatting Viewer written in Rust using wgpu.

flash-attention. Fast and memory-efficient exact attention

robogs. Python

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

InstantMesh. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

3dgs-render-blender-addon. 3DGS Render by KIRI Engine

Mani-GS. [CVPR' 2025'] Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh

mesh2splat. Fast mesh to 3D gaussian splat conversion

Bagel. Open-source unified multimodal model

GenSim2. Python

ReKep. ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

RynnVLA-001. [ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

astro-theme-pure. ⭐ A simple, fast and powerful blog & document theme built by Astro

InternHumanoid. A versatile, all-in-one toolbox for whole-body humanoid robot control.