AI open source rankings.
Code for some of my articles
Pytorch implementation of VQGAN (Taming Transformers for High-Resolution Image Synthesis) (https://arxiv.org/pdf/2012.09841.pdf)
Gemini 3.5 Transcribe demo. Hold a key. Speak. It types. Smart dictation for macOS.
[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.
A Curated Collection of resources for applied AI engineering (work in progress).
(ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
3DUNet implemented with pytorch
RoIAlign & crop_and_resize for PyTorch
AI based tool to convert vocals lyrics and pitch from music to autogenerate Ultrastar Deluxe, Midi and notes. It automatic tapping, adding text, pitch vocals and creates karaoke files.
Security scanner for MCP servers
Implementation of Some Deep Hash Algorithms, Including DPSH、DSH、DHN、HashNet、DSDH、DTSH、DFH、GreedyHash、CSQ.
🚀WebUI integrated platform for latest LLMs | 各大语言模型的全流程工具 WebUI 整合包。支持主流大模型API接口和开源模型。支持知识库，数据库，角色扮演，mj文生图，LoRA和全参数微调，数据集制作，live2d等全流程应用工具
Official community-driven Azure AI Examples
omg.dev — Remote control for claude, codex, cursor, opencode, pi, grok, jcode with mobile client
Official code of PatchmatchNet (CVPR 2021 Oral)
Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.
Create a private chatgpt website via vercel
ChatGPT Gnome Desktop Extension | Talk with ChatGPT from your menubar!
Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch
Image to text, fast.
A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018
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.
这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。
Machine Learning notebooks for refreshing concepts.
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.
Artificial Neural Network
MLOps for DevOps Engineers - A hands-on, project-based guide to Machine Learning Operations
A hub for various industry-specific schemas to be used with VLMs.
🤖一个基于视觉识别，使用自定义YOLO模型，OCR，数据库监听，实现的运行时零侵入的 微信4.0 RPA框架，支持动态接入插件，适配OpenAI，DIfy，支持解析所有消息类型，内置文本图片文件消息发送能力，可扩展小程序朋友圈发送。