Trending Projects

Tacotron-2 is a state-of-the-art text-to-speech model that vibe coders can use to build speech synthesis applications.

This project provides a code repository for the book "Dive into Graph Neural Networks: Understanding GNN Principles".

The Alan AI SDK for Flutter enables building conversational AI-powered apps and voice interfaces.

A comprehensive list of Implicit Representations and NeRF papers relating to Robotics/RL domain.

A header-only C++11 Kalman Filtering Library (EKF, UKF) based on Eigen3, useful for developers working with sensor data and estimation tasks.

A one-stop Transformer library for state-of-the-art code language models and AI-powered code understanding.

A Python SDK/API for reverse-engineered Google Bard, a powerful AI chatbot.

Video anonymization tool that uses face detection to blur or remove faces from video footage.

A pretrained model for detecting lewd images, part of Bumble's image moderation tools.

ELLA: A Python library that equips diffusion models with large language models for enhanced semantic alignment.

Official PyTorch implementation of BigVGAN, a neural vocoder for generating high-quality audio, music, and speech.

A curated list of research papers on visual grounding, a key technique for multimodal AI.

An implementation of Fully Convolutional Networks (FCNs) in TensorFlow for image segmentation tasks.

A recurrent neural network trained on Kanye West's discography to generate new rap songs and lyrics.

A high-performance real-time instance segmentation library for computer vision applications.

A code release for advanced neural radiance field techniques like Mip-NeRF 360, Ref-NeRF, and RawNeRF.

An efficient similarity search library and toolkit for evaluating k-NN methods in non-metric spaces.

A multi-tool for semantic search, enabling advanced natural language processing and information retrieval.

A collection of machine learning lessons and teaching projects designed for engineers.

This repository contains research related to visual and semantic SLAM (Simultaneous Localization and Mapping) for developers working with computer vision and robotics.

A curated list of deep learning resources, including topics like CNN, LSTM, and TensorFlow.

AI-powered image upscaling and restoration tool for developers working with anime, manga, and digital art

A collection of research papers and tools related to using machine learning for compiler and system optimization.

A comprehensive survey of deep learning techniques for 3D point cloud analysis, covering classification, detection, segmentation, and tracking.

A collection of edge/contour/boundary detection papers and toolbox for computer vision tasks.

A Python library for 3D multi-person mesh recovery from monocular images.

A PyTorch-based YOLOv4 and YOLOv5 implementation for detecting fire and smoke in images and videos.

Concise PyTorch implementations of popular deep reinforcement learning algorithms like REINFORCE, A2C, DQN, PPO, DDPG, TD3, and SAC.

Deploy a lightweight ML inference service with a budget-friendly setup in just a few lines of code.

EvTexture is an event-driven video super-resolution library for enhancing video quality using AI.

A library for image restoration without learning, using deep neural networks.

A text classification model using CNN and RNN implemented with TensorFlow for Chinese text data.

GLIDE is a diffusion-based text-conditional image synthesis model that allows developers to generate images from text descriptions.

A collection of Jupyter notebooks showing how to use the Qiskit SDK for quantum computing

An open-source platform for evaluating and improving Generative AI applications with 20+ preconfigured checks and root cause analysis.

A high-performance library for generating state-of-the-art static embeddings for natural language processing tasks.

An open-source, cloud-native platform for machine learning, deep learning, and large language model AI workflows.

Real-time motion retargeting system that maps human movements to diverse humanoid robots on CPU.

This is a Python library for learning to act by watching unlabeled online videos using Video PreTraining (VPT).

A Julia framework for acausal modeling, symbolic math, and parallelized scientific machine learning.

A curated list of resources for Document Understanding (DU) related to machine learning and natural language processing.

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

A differentiable renderer for 3D reasoning and reconstruction, useful for AI-driven 3D applications.

Multimodal AI toolkit for fast content understanding and generation across text, images, and video

A Rust library for reviewing mahjong game logs with a compatible mahjong AI.

A high-performance 3D Gaussian Splatting rasterizer for rendering AI-generated graphics.

Provides enhanced inpainting nodes for the ComfyUI AI generation tool, enabling better image editing and filling capabilities.

Experts.js provides an easy way to create and deploy OpenAI assistants as modular AI agents with expanded memory and attention.

A Jupyter Notebook project that allows searching Unsplash photos using natural language queries.

Content-aware image resize library for Go that uses seam carving and edge detection algorithms.