Trending Projects

CNN for Watermark Removal using Deep Image Prior with Pytorch, a powerful tool for image restoration tasks.

Official code for a CVPR2022 paper on end-to-end video inpainting using optical flow.

R package for evaluating the quality and performance of statistical models in R.

Recipes to scale inference-time compute of open models for AI/ML developers.

FAIR Sequence Modeling Toolkit 2 is a powerful PyTorch-based library for training custom language models and sequence-to-sequence models.

Official PyTorch implementation of a prompt-based distillation method for on-device deployment of the Segment Anything Model (SAM).

A modular voice assistant app for experimenting with state-of-the-art transcription, response generation, and text-to-speech models.

MyoSuite is a collection of environments/tasks for musculoskeletal models simulated with MuJoCo and wrapped in OpenAI gym.

Large-scale 3D scene reconstruction and novel view synthesis using Gaussian representations.

Comprehensive analysis of adversarial threats against AI systems, useful for developers building secure AI applications.

An open-source toolkit for urban spatial-temporal data mining and traffic prediction tasks.

Official implementation of SAM-Med2D, a tool for medical image segmentation using transformers.

This repository contains information about digital humans, likely focused on computer graphics and visualization.

Build AI-powered applications that can see, hear, and speak using screens, mics, and cameras.

3D Point Cloud Annotation Platform for Autonomous Driving

A Python library focused on interpreting the behavior of large language models like OpenAI's GPT-3.

An interactive visualization tool to explore the geometric intuition behind diffusion models.

Neva is a dataflow programming language and compiler that enables parallel computing with static typing.

RAGChecker is a fine-grained framework for diagnosing RAG (Retrieval-Augmented Generation) models.

A Python toolbox for class-incremental learning, a machine learning technique for training models on a continuous stream of data.

Open-source code release for unsupervised object detection and video instance segmentation using AI.

TimeCraft is a time series generation framework for building real-world AI applications.

A curated collection of papers on generative information extraction using large language models.

A Python-based tool to create eye-catching music posters from Spotify data and lyrics.

A WASM vector similarity search library written in Rust for building AI-powered search and recommendation features.

A curated list of gradient boosting research papers with implementations in Python.

A simple API for the VITS text-to-speech model, with additional features for vibe coders.

XuanCe is a comprehensive and unified deep reinforcement learning library for a variety of environments and tasks.

Open-source implementation of the AlphaFold3 deep learning model for protein structure prediction.

A Python library that provides a wrapper around various speech quality metrics for audio processing and analysis.

A multi-view 3D object detection and segmentation framework that uses position embedding transformation.

A research paper on first-order meta-learning algorithms, with associated code in JavaScript.

A real-time AI image generator library powered by TypeScript and modern web technologies.

A Jupyter Notebook project that implements a Chinese version of the LLaMA language model from scratch.

A PyTorch implementation of the UNet++ (Nested U-Net) architecture for image segmentation tasks.

A library for building and training discrete world models for Atari game environments using reinforcement learning.

Online book on neural networks and deep learning, a popular resource for AI and ML developers.

High-quality implementations of reinforcement learning algorithms for AI and machine learning research.

An open-source, high-performance C++ library for real-time face detection in images and video.

Low-code framework for building custom LLMs, neural networks, and other AI models

A collection of Jupyter notebooks showcasing how to build and deploy machine learning models with Amazon SageMaker.

A Python library for secure and private machine learning using federated learning and differential privacy

A JavaScript library for animating 3D poses of human bodies using AI-powered algorithms.

TensorFlow examples repository for developers interested in exploring machine learning and AI capabilities.

A comprehensive cheatsheet covering classical machine learning equations and diagrams.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A fast and optimized implementation of Stable Diffusion with DreamBooth support, for developers building AI-powered tools and applications.

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

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

A library for fine-tuning diffusion models like Stable Diffusion using Low-Rank Adaptation (LoRA) for quick and efficient model personalization.