Trending Projects

Automate your mobile devices with natural language commands using an LLM-agnostic mobile agent.

A faster PyTorch implementation of the Faster R-CNN object detection algorithm.

A guide for preparing for technical interviews in machine learning and AI topics.

Curated collection of AI-generated images and prompts showcasing the advanced capabilities of GPT-4o and GPT-Image-1.

Provides AI-powered tools and samples for developers to build cutting-edge applications with Microsoft AI.

A Chinese translation of Machine Learning Yearning, a book by Andrew Ng on best practices for machine learning projects.

A Swift-based library for running Stable Diffusion AI models natively on Apple Silicon Macs.

An AI-powered image generation tool that can create high-quality images from text prompts.

A series of large language models trained from scratch by developers @01-ai for vibe coders.

BabelDOC is a Python-based document translation tool that leverages AI to enable multilingual communication.

A PyTorch-based text-to-speech model that generates high-quality speech with expressive prosody.

An open-source face recognition system with a rich set of computer vision features and APIs.

A collection of TensorFlow 2.0 tutorials in Chinese for developers to learn AI and machine learning.

An agent framework for fintech and banks, with support for AI tools like OpenAI and LLMs.

A comprehensive roadmap for learning essential machine learning concepts and tools.

A Python library for fast, high-quality monocular view synthesis, useful for computer vision and 3D applications.

Cartographer is a real-time SLAM system for 2D and 3D localization and mapping across multiple platforms and sensors.

This repository is an experiment in using reinforcement learning to play the classic Pokemon Red video game.

An open-source Python tool that uses AI to remove backgrounds from images and videos with a simple command line interface.

A comprehensive SDK for running frontier LLMs and VLMs on multiple hardware platforms with day-0 model support.

A library that removes signs of AI-generated writing from text, helping developers identify authentic content.

AI-powered wearable device that transcribes speech and summarizes conversations for developers.

An open-source GPT-based AI assistant that integrates with LINE and Vercel for easy deployment

A TypeScript library that provides a free OpenAI GPT-4 API, enabling developers to build AI-powered applications.

This is an implementation of the Dreambooth technique for fine-tuning Stable Diffusion models.

A powerful Python NLP library for tokenization, sentence segmentation, named entity recognition, and parsing of many languages.

A production-ready AI retrieval system with a RESTful API, built using Agentic Retrieval-Augmented Generation (RAG).

SPADE is a Python library for semantic image synthesis, enabling high-quality generation of images from semantic segmentation maps.

TensorRT implementation of popular deep learning networks for efficient inference on GPUs

ERNIE is an industrial-grade development toolkit based on PaddlePaddle for building AI-powered applications.

A repository for a book on understanding the fundamentals of deep learning.

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

An open-source bilingual pre-trained language model that can be used for a variety of NLP tasks.

AlphaFold 3 is a Python-based inference pipeline for protein structure prediction using deep learning.

A highly capable foundation model for monocular depth estimation, a key component in computer vision.

A multilingual voice understanding model for AI-powered audio analysis and transcription.

A powerful Android RPA agent framework for mobile automation and security testing.

LMDeploy is a toolkit for compressing, deploying, and serving large language models (LLMs).

An image-to-image AI tool that helps developers create and refine their designs and visuals.

This repository contains a diffusion model for generating expressive portrait videos from audio.

A comprehensive collection of resources for large language models, including AI coding tools, MCP frameworks, and more.

An open-source Python library for automated feature engineering in machine learning.

Distributed Asynchronous Hyperparameter Optimization in Python for machine learning models.

A Chinese version of the GPT-2 language model training code, using the BERT tokenizer.

CodeGeeX2 is a powerful multilingual code generation model for AI-powered coding tools and workflows.

A detailed guide for undergraduate students or anyone wanting to dive into the field of AI with a solid foundation.

An open-source library that allows developers to inpaint images using Segment Anything and state-of-the-art inpainting models.

A collection of Variational Autoencoders (VAEs) implemented in PyTorch for deep learning research and applications.

A Retrieval Augmented Generation (RAG) chatbot powered by Weaviate, a modern vector database for AI applications.

A sample app for the Retrieval-Augmented Generation pattern using Azure AI Search and Azure OpenAI large language models.