Trending Projects

Aircraft design optimization made fast through computational graph transformations and composable analysis tools.

An open-source platform for creative visual effects and media generation using AI tools

This repository contains the book 'Machine Learning Yearning' by Andrew Ng, a renowned expert in machine learning.

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

Official PyTorch implementation of a state-of-the-art virtual try-on model for high-resolution clothing generation.

A comprehensive collection of Transformer models for natural language processing tasks

Sora AI Video Generator is a TypeScript library for generating AI-powered videos for content creators and developers.

Pruna is a model optimization framework that helps developers deliver faster, more efficient AI models with minimal overhead.

A lean C++ library for working with point cloud data, with support for various 3D data processing tasks.

Examples of programs built using the Modal serverless platform for AI and machine learning applications.

A live coding session by Christopher Wolfram exploring content from the 2016 film Arrival using the Wolfram Language.

An AI-powered tool for anime image inpainting and restoration, useful for computer vision and generative art projects.

A computer vision curriculum and tutorials for developers interested in machine learning and AI.

A fast, general, and tested differentiable structured prediction library for PyTorch.

A Python-based GUI tool for generating subtitle files from videos using a Transformer-based framework.

MASS is a pre-training framework for language generation tasks using masked sequence-to-sequence learning.

Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds

An OWASP project that provides security guidance for developers building applications with large language models (LLMs).

A lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for machine learning.

Attention-based OCR library for building vision AI apps that extract text from images.

FAIR Sequence Modeling Toolkit 2 is a powerful PyTorch-based library for training custom language models and sequence-to-sequence models.

A Python library for predicting depth maps from single RGB images using a fully convolutional residual network (FCRN).

A collection of hacks and techniques for training reinforcement learning systems from a Deep RL Bootcamp lecture.

A PyTorch toolkit for 2D Human Pose Estimation, useful for developers working on computer vision and AI-powered applications.

Official PyTorch implementation of a prompt-based distillation method for on-device deployment of the Segment Anything Model (SAM).

Official PyTorch implementation of Cold-Diffusion, a technique for different transformations.

A ComfyUI extension that allows developers to interrogate booru tags from images, useful for vibe coders.

A C++ inference library for various SVC/TTS models, including DiffSinger, DiffSVC, HiFiGAN, and VITS.

A comprehensive curriculum for learning machine learning and AI development in Python.

A SQL-driven RAG engine that automatically builds a knowledge graph during querying, enabling knowledge-enhanced applications.

Advanced evolutionary computation library built on PyTorch for AI and machine learning applications.

A 3D reconstruction library with spatial memory for computer vision applications.

A multi-modal and multi-scenario dataset for ground robots research and SLAM applications.

TerraBrush is a C++ library for procedural terrain generation, providing tools for vibe coders to create dynamic and realistic environments.

A TypeScript framework for building AI-powered applications and tools.

A TensorFlow-based rotation detection benchmark for computer vision and AI models.

A lightweight C++ library for using Keras (TensorFlow) models in edge computing and embedded applications.

A high-quality deep learning-powered tool to remove Sora2 watermarks from images.

This repo contains a 1D tokenizer and generator, potentially useful for AI coding tools and research.

A toolbox for spectral compressive imaging reconstruction with state-of-the-art algorithms.

A web app that uses AI to convert text to Mermaid code and render it as visualizations.

Tau-Bench is a Python library for benchmarking and evaluating AI language models and tools.

A computer vision library for developers working with AI tools and models.

Efficient architectures for interactive conditional GANs, useful for image-to-image translation tasks.

A deep learning-based library for classifying the genre of audio files.

A single-header-only modern ray tracing kernel for vibe coders building AI-powered graphics apps.

Hephaestus is a semi-structured, agentic framework that allows workflows to build themselves as agents discover what needs to be done.

A library of chest X-ray datasets and models for medical AI/ML applications.

Source code for a research paper exploring the relationship between self-attention and convolutional layers.

Lhotse is a set of tools for handling multimodal data in machine learning projects, with a focus on speech and audio.