Trending Projects

A deep learning-based point tracking library for computer vision and robotics applications.

A curated list of Graph/Transformer-based papers and resources for fraud, anomaly, and outlier detection.

A deep learning-powered library for detecting and recognizing Chinese license plates, including support for 12 different plate types.

Command line tool for forced alignment using the Kaldi speech recognition toolkit.

A suite of tools that enable developers to build and monitor AI systems more responsibly.

A self-supervised video representation learning model for video understanding tasks.

Bailing is an open-source AI voice assistant built with ASR, LLM, and TTS, supporting low-latency response on low-end devices.

Open-source tools for computational pathology and digital pathology research using deep learning and weakly-supervised learning.

A Python library for generating physically stable 3D toy brick models from text prompts.

A TypeScript-based open-source project for building AI-powered group chat applications.

A Python library for deep probabilistic analysis of single-cell and spatial omics data.

A Python library that uses LLMs and embeddings to process datasets with up to 1000x speedups

A Python library that provides native multimodal models for building world-learning AI systems.

The official code repository for the second edition of the book Generative Deep Learning, covering AI models and techniques.

MAESTRO is an AI-powered research application that streamlines complex research tasks.

A simple GUI for ByteDance's Piano Transcription with Pedals, built using the Nix programming language.

A modern model graph visualizer and debugger for AI developers building with AI tools.

This repository contains scripts, models, and files for the Deep Noise Suppression (DNS) Challenge, a tool for developers working with audio processing and AI.

A .NET/C# binding for Baidu's Paddle Inference library and PaddleOCR, enabling AI/ML integrations.

A platform for accelerating embodied AI research, with a focus on robotics and simulation.

SudoLang is a TypeScript library that provides LLM (Large Language Model) support for Visual Studio Code.

This is a library for sparse representation and high-resolution 3D shape modeling, useful for computer graphics and vision tasks.

Replicable multi-agent reinforcement learning library with support for PyTorch, Ray, and RLlib.

A library for using large and small language models together in machine learning applications.

LeanCopilot is a C++ library that uses large language models (LLMs) as copilots for theorem proving in the Lean programming language.

TrustRAG is a Python framework for building reliable and trusted Retrieval Augmented Generation (RAG) models.

FinRL Tutorials - a collection of Jupyter Notebooks for financial reinforcement learning.

PromptChains helps developers maximize the intelligence and results of their prompts when using large language models (LLMs).

A minimal implementation of DeepMind's Genie world model for AI and machine learning research.

NotaGen is an AI-powered tool for generating symbolic music by leveraging large language models.

A robust dense feature matcher for estimating pixel-dense warps and reliable certainties between image pairs.

A curated list of ML videos, links, projects and datasets to help developers learn and master machine learning.

A lightweight, fast, and OAI-compatible API server for Exllama, a developer discovery platform focused on AI-driven vibe coders.

A frontier multimodal foundation model for advanced image and video understanding tasks.

Official PyTorch implementation of a scalable transformer-based generative model for image generation and manipulation.

A JavaScript engine optimized for use in the Lynx platform, a developer discovery platform for vibe coders.

A Python library for generating AI-driven content using the Fusion Infinity Generator.

This GitHub repository is a collection of public person re-identification datasets, which are useful for computer vision and AI research.

A versatile image inpainting model that supports various AI-powered image editing capabilities.

Generate 3D objects conditioned on text or images using a pre-trained AI model.

An open-source real-time object detection library powered by the YOLOv10 neural network model.

YOLOv3 is a popular open-source object detection library for computer vision tasks, with support for multiple deployment targets.

A comprehensive repository for computer vision best practices, code samples, and documentation.

An open-source Python library that allows users to convert images and videos to ASCII art.

Open-source implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model.

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

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

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

Official PyTorch implementation of StyleGAN3, a state-of-the-art generative adversarial network (GAN) for creating realistic images.

An AI-powered, parametric QR code generator that allows developers to create unique and artistic QR codes.