Trending Projects

Production infrastructure for running machine learning models at scale

A Go library for generating high-quality triangulated and polygonal art from images using evolutionary algorithms.

An R library for detecting anomalies in time series data using statistical models.

A library for training multilingual word embeddings, useful for NLP tasks across languages.

A collection of TensorRT demos for object detection, image classification, and other computer vision tasks.

A Python tool that allows users to edit images generated by the Stable Diffusion AI model

The google-research/pegasus repository is a Python library for training and using the PEGASUS language model for abstractive text summarization.

Kernl is a library that lets you run PyTorch transformer models several times faster on GPU with a single line of code.

PyTorch extensions for fast R&D prototyping and Kaggle competition tools

This TensorFlow code implements a curiosity-driven exploration algorithm for deep reinforcement learning.

Omniglot dataset for one-shot learning experiments in MATLAB

A Python library for quickly editing and fine-tuning large language models like GPT, BLOOM, and LLAMA.

A C++ library for solving exercises in the book 'Probabilistic Robotics' for autonomous vehicle and robotics development.

Open Multilingual Chatbot for Everyone, a chatbot platform for building and deploying conversational AI agents.

Optimizes numerical and discrete search spaces with various gradient-free optimization techniques.

A Cantonese programming language compiler written in Rust for vibe coders building AI tools.

An open-source quantum computing framework for building, running, and optimizing quantum algorithms.

A C# framework for computer vision, artificial intelligence, and other research-oriented tasks.

A state-of-the-art AI text-to-GIF model for developers building with AI tools and Stable Diffusion XL.

A Python benchmark suite for evaluating text-to-3D generation models and techniques.

A book on SLAM (Simultaneous Localization and Mapping) that covers geometric methods and deep learning approaches.

TableBank is a benchmark dataset for table detection and recognition, useful for building computer vision models.

SeetaFaceEngine is a C++ library for facial recognition and detection.

HiPlot is a TypeScript library that makes understanding high-dimensional data easy for developers.

brat is a rapid annotation tool for textual data, useful for AI/ML data annotation tasks.

A neural network model for Chinese named entity recognition written in Python.

A personal knowledge management system and digital garden for Swyx, a developer focused on building with AI tools.

On-line Machine Learning library in Go for building AI-powered applications.

PaddleSlim is an open-source library for deep model compression and architecture search.

Infer.NET is a C# framework for running Bayesian inference in graphical models, useful for machine learning.

A PyTorch implementation of Deformable Convolution Networks V2 (DCNv2), a powerful computer vision technique.

Use pre-trained transformer models like BERT, GPT-2, and XLNet in the spaCy NLP library.

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices.

A starter kit to build local-only AI apps that cost $0 to run, focused on document Q&A.

A PyTorch library for semantic segmentation, a computer vision task to classify each pixel in an image.

A collection of pre-trained computer vision models for developers building AI-powered applications.

Official implementation of X-Decoder, a generalized decoding model for pixel, image, and language tasks.

A high-performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

An extension for Auto1111 Stable Diffusion webui that adds text-to-video diffusion models like ModelScope or VideoCrafter.

A Python implementation of the node2vec algorithm for learning embeddings from graph-structured data.

Neural model for converting Image-to-Markup, a useful tool for developers building AI-powered applications.

A powerful GAN-based text-to-image synthesis model for fast large-scale image generation.

Powerful SOTA computer vision model for various image enhancement tasks like denoising, deblurring, and more.

A lightweight and efficient LiDAR odometry solution for accurate localization and 3D mapping in robotics.

A no-code machine learning exploration tool that lets developers learn about ML without coding.

Olivia is an open-source, AI-powered voice assistant that can be used to build conversational applications.

A research project on Fully Convolutional Networks for Semantic Segmentation, a key computer vision technique.

This is a PyTorch implementation of Cross-lingual Language Model Pretraining, a research project focused on multilingual NLP.

An open autoregressive foundational video AI model for vibe coders building with AI tools.

A Chinese OCR (Optical Character Recognition) library built using CTPN, DenseNet, and CTC.