Trending Projects

A cleaned and curated version of the Alpaca dataset from Stanford, useful for machine learning projects.

An AI-powered companion tool for reading and understanding academic research papers.

A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources.

This is a combined repository for the RTX-Remix runtime and toolkit, focusing on path-tracing and RTX features.

A TypeScript-based open-source project for building AI-powered group chat applications.

A Python library that provides agent techniques to augment and push the limits of large language models (LLMs).

Code and models for Temporal Segment Networks (TSN) for action recognition in video understanding.

A self-driving MarioKart game built with TensorFlow, a powerful machine learning library.

An AI-powered tool that extracts knowledge and generates summaries from PDF books, page by page.

Distributed deep learning library for Keras and Spark, enabling scalable training of neural networks.

A project that helps automate the creation and distribution of short-form and long-form video content across social media platforms.

An open-source Korean language model for understanding natural language instructions.

This repository provides a dual LSTM encoder model for generating dialog responses using machine learning.

A Python-based library for generating videos from code, focused on the vibe coding and AI tools ecosystem.

A collection of must-read papers on adversarial attacks and defenses for natural language processing.

A minimalistic implementation of the Self Organizing Maps (SOM) algorithm for clustering and dimensionality reduction.

A Python library for deep probabilistic analysis of single-cell and spatial omics data.

Official implementation of a controllable character video synthesis model using spatial decomposed modeling.

A Java toolkit for text similarity calculation and sentiment analysis, useful for NLP tasks.

A toolkit for 3D reconstruction and structure-from-motion computer vision tasks.

A work-in-progress chess bot written in C# for developers interested in building chess AI.

An open-source framework for detecting, highlighting, and correcting grammatical errors in natural language text.

AI-powered news aggregator that summarizes Twitter/RSS feeds with structured summaries and web dashboard

A PyTorch implementation of the Non-local Block, a key component in computer vision models.

A research paper on representation alignment for training diffusion models for AI-assisted code generation.

Converts any music library into a sample-library using machine learning techniques.

An ensemble sampling toolkit for affine-invariant Markov Chain Monte Carlo (MCMC) in Python.

NICE-SLAM is a neural implicit approach for scalable 3D reconstruction and localization.

A high-level deep learning framework written in Kotlin and inspired by Keras.

A C++ library that enables deploying the YOLOv5 object detection model on mobile devices using the NCNN framework.

A C++ library for real-time behavior synthesis using the MuJoCo physics simulation engine and model predictive control.

DeepAA is a Python library that uses deep learning to generate ASCII art from images.

High-quality implementations of standard and state-of-the-art methods for Bayesian and probabilistic machine learning.

PyTorch extensions for fast R&D prototyping and Kaggle competition tools

An open-source feature selection repository in Python for machine learning tasks.

A diffusion-based generative model for creating novel views and videos from static images.

FCIS is a library for instance-aware semantic segmentation, a computer vision technique useful for AI and robotics applications.

Spearmint is a Bayesian optimization codebase for AI and machine learning experiments.

A toolkit to optimize machine learning models for deployment, including quantization and pruning.

In-depth tutorials for implementing deep learning models with PyTorch, a popular machine learning framework.

A PyTorch implementation of YOLOv2, a fast and accurate object detection model.

An efficient C++ implementation of the RWKV language model for fast CPU inference on various bit-width quantizations.

This 2D Unity simulation allows cars to learn to navigate through different courses using a feedforward neural network and genetic algorithm.

A high-performance text-to-3D generation model for building immersive 3D experiences with AI tools.

Open-source implementation of Google Vizier for hyper parameters tuning in machine learning models.

An implementation of the 3D Ken Burns Effect from a single image using PyTorch.

Measuring Massive Multitask Language Understanding with GPT-3 and few-shot learning techniques.

A curated list of resources for meta-learning, including papers, code, books, and more for developers working with AI tools.

A lightweight parameter server interface for distributed machine learning applications.

Octo is a transformer-based robot policy trained on 800k robot trajectories for vibe coders.