Trending Projects

AIDE is an AI-driven machine learning engineering agent that automates AI R&D tasks for developers.

A Python library for generating expressive talking video using memory-guided diffusion models.

A PyTorch implementation of the I3D (Inflated 3D ConvNet) architecture for video classification tasks.

Central repository for the engineering and scaling working group of the BigScience AI research project.

A collection of machine learning blogs and code samples, focused on algorithms, reinforcement learning, and scikit-learn.

An autonomous LLM agent for solving complex tasks, with a focus on AI-assisted coding and task automation.

An optimizer that trains as fast as Adam and as good as SGD, useful for AI/ML developers.

A comprehensive set of fairness metrics and algorithms to detect and mitigate bias in AI/ML models and datasets.

High-performance machine learning algorithms with 2-2000x speed and 50% less memory usage for all hardware.

PyTorch implementation of the Squeeze-and-Excitation Network (SENet) architecture for deep learning models.

A collection of scripts and utilities for the Cityscapes Dataset, a popular dataset for computer vision tasks.

A library for understanding and improving diffusion-based generative models, a key technique in AI-powered creative tools.

This repository contains the original code from the DeepMind Atari Deep Q-Learner article with some tweaks.

Powerful, fast, and efficient unstructured data extraction library written in Rust with language bindings.

This is a Python library for audio tagging using a convolutional neural network model trained on the AudioSet dataset.

ModernBERT brings the BERT language model into the modern era with architecture changes and scaling.

A roadmap to become a Visual SLAM (Simultaneous Localization and Mapping) developer in 2023.

A Transformer-based sensor fusion model for end-to-end autonomous driving.

An open-source AI-powered chatbot that can be used for various conversational tasks.

An extensive collection of resources for developers interested in talking face synthesis using AI tools.

A curated collection of papers related to Mamba, a framework for building AI-powered applications.

A Julia library for CUDA programming, enabling high-performance GPU computing on a wide range of NVIDIA hardware.

A deep learning-based framework for Structure from Motion (SfM) from visual geometry.

Code and data for enhancing photorealism, focusing on AI-powered image manipulation tools.

The Simple Agent Development Kit for building AI-powered software agents and bots.

A lightweight, local-first, and free experiment tracking library for AI/ML developers from Hugging Face.

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

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

An open-source library for object tracking using YOLOv8 and DeepSORT algorithms, suitable for vehicle counting and speed estimation applications.

A Python package for uncertainty quantification and hallucination detection in large language models (LLMs)

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

A lightweight face detection model with landmark detection, useful for building computer vision applications.

A Python library for training and using StyleGAN2, a popular deep learning-based image generation model.

A simple, state-of-the-art NLP framework for tasks like named entity recognition and semantic role labeling.

instruct-pix2pix is a Python library that allows generating images from text prompts using AI models.

A Python library that provides various text embedding and similarity models, including Word2Vec, Sentence-BERT, and more.

A TypeScript-based tool for converting natural language queries into SQL using AI.

A PyTorch-based package of deep learning-based CTR models for easy-to-use, modular, and extendible development.

A collection of top solutions for various data competitions, useful for vibe coders working with AI tools.

A diverse and well-annotated dataset for license plate detection and recognition

A Chrome extension that uses Meta's Segment Anything Model to extract and copy objects from images.

A fully functional poker bot that uses computer vision, neural networks, and genetic algorithms to play poker on various platforms.

A dynamically typed scripting language written in Rust for vibe coders and AI-powered development.

A memory-efficient library for training large language models (LLMs) using gradient low-rank projection.

Official PyTorch implementation of Magic123, a tool for generating high-quality 3D objects from a single image using 2D and 3D diffusion priors.

A Python library for training and detecting objects using the YOLO3 deep learning algorithm.

A high-performance, autoregressive model for generating high-resolution images from text prompts.

Phantom is a subject-consistent video generation tool that aligns text and video via cross-modal alignment.

A PyTorch Lightning code guideline and template for building deep learning projects.

VideoLLaMA 2 is a Python library that advances spatial-temporal modeling and audio understanding in video-based large language models.