Trending Projects

A comprehensive tutorial on practical AI and machine learning, with Jupyter Notebook examples.

Qwen-VL is a large vision language model proposed by Alibaba Cloud for AI-powered coding and development.

A repository that collects, organizes, and publishes Chinese natural language processing (NLP) datasets to advance the development of Chinese NLP.

A Python toolkit for text error correction, featuring models like Kenlm, T5, MacBERT, and ChatGLM3.

Enchanted is an iOS and macOS app for chatting with private self-hosted language models like Llama2, Mistral or Vicuna using Ollama.

A visual playground for agentic workflows to iterate over agents 10x faster with AI tools and LLMs.

A toolbox for 3D object detection using LiDAR point clouds, focused on autonomous driving use cases.

An open-source cloud-native AI platform for ML/DL workflows, model serving, and distributed training.

A TypeScript-based open-source API that provides a reverse-engineered interface to the Kimi AI large language model, with features like stream output, smart agent dialogue, and document parsing.

DouZero is a deep reinforcement learning framework for mastering the Chinese card game DouDizhu.

This repository provides everything needed to build a Retrieval Augmented Generation (RAG) application using the LangChain framework.

A 3D computer vision framework for 3D reconstruction, camera tracking, and photogrammetry.

A minimalist environment for decision-making in autonomous driving powered by reinforcement learning.

This repository provides guidance on optimizing algorithms for CUDA, a framework for parallel computing on NVIDIA GPUs.

SMPL-X is a Python library for working with the SMPL-X human body model.

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

A repository that contains interview notes and questions related to large language models (LLMs) for algorithm engineers.

FinGLM is an open, public, and sustainable financial large model project that promotes AI+Finance using open source.

Official implementation of iTransformer, an effective transformer-based time series forecasting model.

An open-source, real-time, and streaming interactive world model for developers building AI-powered applications.

A differentiable PDE solving framework for machine learning tasks that leverage fluid simulations.

A toolkit for easier and faster deployment of YOLO (You Only Look Once) object detection models using NVIDIA TensorRT.

An open-source diffusion-based multimodal LLM framework for unified understanding and generation.

The Hylo programming language is a new open-source language focused on building AI-powered applications.

This repository contains the source code for a tool to analyze the real context size of long-context language models.

Step-Audio 2 is an end-to-end multi-modal large language model for industry-strength audio understanding and speech conversation.

A platform for developers to discover, learn, and experiment with state-of-the-art AI models.

A 3D-informed video generation model with precise camera control for high-quality, consistent video content.

Efficient communication library for GPUs, covering collectives, P2P, and EP for AI/ML workloads

Reverse-engineered API for the Alibaba Tongyi Qwen 2.5 large language model, providing AI capabilities like image generation, document analysis, and conversational AI.

Distribute and run AI workloads on Kubernetes with a Python-based infrastructure toolkit like PyTorch.

A collection of research papers on autonomous agents and large language models (LLMs) updated daily.

A ComfyUI extension that allows developers to interrogate booru tags from images, useful for vibe coders.

HYPIR is a Python library for image restoration and super-resolution using diffusion-based priors.

A Python library that boosts cost efficiency, inference accuracy, and cross-domain adaptability for complex QA systems.

Python implementation of the reinforcement learning concepts from the classic textbook.

A lip sync generation tool that leverages AI to synchronize speech with video in the wild.

CoreNLP is a comprehensive NLP toolkit that provides powerful language processing capabilities for Java developers.

A curated list of reinforcement learning resources for developers interested in this field of AI.

Bob is a macOS app that provides translation and OCR capabilities for developers who work with AI tools.

A robust and highly performant video matting library for PyTorch, TensorFlow, TensorFlow.js, ONNX, and CoreML.

NSFW detection on the client-side via TensorFlow.js for content moderation and filtering.

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

OpenFace is a state-of-the-art tool for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

PyTorch code for training Vision Transformers using the Self-Supervised DINO learning method.

A Python-based library for solving visual understanding tasks using reinforced visual-linguistic models (VLMs).

A roadmap to learn Generative AI tools and technologies in 2025

A computer vision and sports analytics library for building sports-focused AI applications.

Notebooks using the Hugging Face libraries, a popular set of tools for building AI-powered applications.

An open-source, camera-only framework for autonomous driving perception tasks like 3D object detection and semantic map segmentation.