Trending Projects

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

Postgres-based database with GPU acceleration for machine learning and AI applications.

Causal inference and uplift modeling library for machine learning applications.

Evolutionary Scale Modeling (ESM): Pretrained language models for proteins in Python.

A MATLAB library for joint face detection and alignment using multi-task cascaded convolutional neural networks.

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

A curated reading list for security, safety, and privacy of large language models (LLMs) and AI systems.

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

Open-source codebase for a paper on using evolution strategies for scalable reinforcement learning.

Tutorials and implementations for self-normalizing neural networks, a type of AI model.

Causal Discovery in Python, including independence tests and score functions for causal inference.

NCCL Tests - a library for efficient multi-GPU collective communication primitives for NVIDIA GPUs

A C++ powered OCR tool that outputs JSON for easy integration with other programs.

Attention-based model for learning to solve different routing problems, useful for AI coding tools.

A new padding scheme for convolutional neural networks using partial convolution-based padding.

A Home Assistant integration and model to control your smart home using a local large language model.

Official implementation of a CVPR 2024 paper on deformable 3D Gaussians for monocular dynamic scene reconstruction.

A curated collection of recent advances in vision-language pretrained models (VL-PTMs) for AI and multimodal applications.

A Python framework that enables parallel analysis of any query using specialized AI agents.

VideoGPT is a Jupyter Notebook-based project for generating videos from text prompts using AI models.

Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation.

A natural language detection library for Rust that can identify the language of text samples.

MotionDirector is a diffusion-based text-to-video generation tool focused on customizing motion for AI-generated videos.

Simple reference implementation of GraphSAGE, a graph neural network framework for machine learning.

An explainable GNN (Graph Neural Network) library for interpreting and understanding GNN models.

A C++ toolkit for building real-world machine learning and computer vision applications.

A powerful mixture-of-experts vision-language model for advanced multimodal understanding.

Jupyter notebooks for the Natural Language Processing with Transformers book, focused on AI-powered language models and tools.

A Python library for creating videos using the Stable Diffusion text-to-image AI model, with exploration of the latent space.

A comprehensive machine learning glossary and cheatsheet for data scientists and AI developers.

Open-source CodeT5 language models for understanding and generating code

This repository provides a tutorial and code for implementing the YOLO v3 object detection algorithm from scratch using PyTorch.

A library of machine learning methods for chemistry research, built by Facebook's AI research team.

Official implementation of a library for representing functions using periodic activation functions

Simple, hackable offline speech-to-text tool using the VOSK-API, useful for vibe coders building AI apps.

A dataset and pretrained model for detecting safety helmet wearing, useful for computer vision projects.

A Python library for differentiable robotics and pose estimation using deep learning and optimization.

A Python library for semantic segmentation using a novel masking-based approach.

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

A library for implementing hyperparameter optimization methods for machine learning and deep learning models.

A Python tool for reading prompts from Stable Diffusion generated images outside the web UI.

An AI-powered image matting library for image background removal, format conversion, and compression.

Comprehensive collection of 300+ AI agent resources for developers building with AI tools.

An AI framework for games based on the libGDX library, featuring steering behaviors, pathfinding, and more.

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

TensorFlow Text is a library for working with text data in TensorFlow, making text a first-class citizen.

A TypeScript framework for building multi-agent AI applications with coordinated, efficient collaboration.

A comprehensive collection of deep learning paper reviews and code practices for AI developers.

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

A zero-knowledge protocol for anonymous interactions, built with TypeScript and used in Ethereum applications.