Trending Projects

A beginner-friendly Vulkan path tracing tutorial in under 300 lines of C++.

A toy Python implementation of the GloVe word embedding algorithm, useful for NLP developers.

A curated list of attention modules and plug-and-play modules for computer vision in Python.

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

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

A Python library for integrating visual intelligence into Home Assistant, a popular home automation platform.

AgentEvolver is a Python library for building self-evolving agent systems powered by large language models and reinforcement learning.

An open-source Python library for improving the quality of audio signals using neural networks.

Easy-to-use, state-of-the-art neural machine translation library for 100+ languages.

A powerful library for photographic image synthesis using cascaded refinement networks.

This codebase demonstrates how to synthesize realistic 3D character animations from speech input and a static mesh.

High-performance Rust stream processing engine that seamlessly integrates AI capabilities for real-time data processing.

A large-scale image-text dataset for training AI models, primarily focused on visual AI and multimodal AI tasks.

DriveLM is a graph visual question answering model for autonomous driving tasks, built using large language models.

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation using PyTorch.

NVIDIA DLSS is a deep learning neural network that boosts frame rates and generates sharp images for games.

Interactively explore unstructured datasets like audio, images, and video using this TypeScript library.

A Python library for visualizing Artificial Neural Networks (ANNs) for vibe coders working with AI tools.

Matcha-TTS is a fast and efficient text-to-speech (TTS) architecture using a conditional flow matching approach.

A robust, efficient, and adaptable toolkit for segmenting text into sentences or other semantic units.

ZeroSearch: A Python library that incentivizes the search capability of large language models without actually searching.

Official code for DragDiffusion, a CVPR 2024 highlight for AI-powered image editing.

A Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation

Guidance for training an AWS DeepRacer model using Amazon SageMaker, providing developers full control over the process.

Fast and embedded solvers for nonlinear optimal control and nonlinear model predictive control

This Python library speeds up the Qwen-Image model using distillation, a technique for AI model optimization.

An AI-powered image editing tool that allows users to generate images by providing example content.

An open-source toolkit for analyzing the internal workings of Transformer-based language models.

A fast local neural text-to-speech engine for Mycroft, an open-source voice assistant.

R-FCN: Object Detection via Region-based Fully Convolutional Networks - a Matlab library for computer vision tasks.

A PyTorch-based library for named entity recognition using the BERT language model.

A TypeScript SDK for building AI-powered web applications and tools

Avatarify is a desktop application that allows you to animate your face and create realistic videos with AI.

A Python library for building Bayesian statistical models and performing Bayesian inference.

Fine-tune LLMs with online reinforcement learning for building AI-powered applications and agents.

An open-source AI-powered platform for cyber threat intelligence and hunting, built with Django and React.

A Python library for estimating the 6D object pose using dense fusion of RGB and depth data.

A collection of paper reading notes on deep learning and machine learning topics.

This repository provides hands-on examples and guidance for building, training, deploying and maintaining deep learning models in production.

Granite Code Models: A family of open foundation models for building code intelligence applications.

A high-performance image synthesis model with improved distribution matching distillation.

An all-in-one model for offline and simultaneous speech recognition, translation, and synthesis.

A framework for encrypted machine learning in TensorFlow, enabling confidential computing and privacy-preserving AI.

LangChain for Rust, the easiest way to write LLM-based programs in Rust

A comprehensive survey of task-oriented dialogue research, including datasets and state-of-the-art methods.

Official implementation of a generative motion modeling framework for 3D human motions.

This repository provides a series of GPU optimization topics and CUDA kernel optimizations for high-performance computing.

Solution for the Data Science Bowl 2017 competition, focused on AI-powered coding and tools.

A Python library for planning with diffusion models to enable flexible behavior synthesis.

Boosts the deployment and serving of deep learning models and web services.