Trending Projects

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

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

A Python package for uncertainty quantification and hallucination detection in large language models (LLMs)

A PyTorch-based audio processing library for spectrograms, CQT, and neural network-based preprocessing.

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

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

A Python library for training and using AI models in the ComfyUI AI generation tool.

Res2Net-PretrainedModels is an official PyTorch implementation of the Res2Net multi-scale backbone architecture for computer vision tasks.

Automated, hardware-independent Hand-Eye Calibration tool for robotics and computer vision applications.

An open-source text-to-speech server built with Python, useful for adding voice functionality to applications.

A zk-SNARK library written in Rust for building cryptographic applications.

A curated list of resources for realistic image composition and object insertion using AI and computer vision techniques.

Sample Node.js application for the IBM Watson Speech to Text service

A flexible and powerful library to develop your own Transformer variants for AI/ML applications.

A comprehensive collection of deep learning interview questions for developers building with AI tools.

A state-of-the-art AI text-to-GIF model for developers building with AI tools and Stable Diffusion XL.

ToRA is a series of Tool-integrated Reasoning LLM Agents for solving mathematical reasoning problems.

End-to-end Chinese license plate recognition using MXNet, a machine learning framework.

A repository for learning TensorFlow, a popular open-source machine learning library in Python.

Large-scale 3D scene reconstruction and novel view synthesis using Gaussian representations.

A PyTorch implementation of the Style-Based GAN architecture for generative adversarial networks.

Implementation of the QuickDraw game, a computer vision and deep learning project focused on image classification.

Sample code for the Google Cloud Vision API, a powerful computer vision tool for image analysis.

Tools to train a generative model on arbitrary audio samples for vibe coders focused on AI tools.

Portfolio optimization tool using deep learning and PyTorch for finance and wealth management.

Read Pilot is an AI-powered tool that analyzes articles and generates Q&A cards, built with Next.js and OpenAI.

Offline Russian voice assistant with plugin-based skills for developers working with AI tools.

This Python project provides utilities to convert datasets to COCO and VOC formats for object detection tasks.

SETR is a transformer-based approach for rethinking semantic segmentation from a sequence-to-sequence perspective.

This repository provides projects for monocular depth estimation and 3D scene reconstruction from single images.

A Python and PyTorch-based AI voice assistant for hackers, with features like speech recognition and generation.

A curated collection of resources for ChatGPT, the popular AI language model, including tools, documentation, and use cases.

Command-line tools for speech and intent recognition on Linux, focused on voice-based AI applications.

This repository provides tools and models for training LoRA (Low-Rank Adaptation) for large language models like LLaMA and ChatGLM, enabling AI-powered code generation and assistance.

A toy path tracer for learning purposes, with support for CPU/GPU, C++/C#, Win/Mac/Wasm, DX11/Metal, and Unity.

A tool for structurally pruning large language models like LLaMA, BLOOM, and Vicuna to reduce their size and inference time.

An A3C algorithm implementation for training an AI agent to play Super Mario Bros

Open-source projects related to trustworthy AI, including causal discovery, causal inference, and causality.

A dataset and reinforcement learning algorithm for endowing audio language models with bimodal reasoning abilities.

CogView4 is a high-resolution, text-to-image AI model for vibe coders focused on image generation.

An AI-powered Chrome extension that enables natural language search within web pages using BERT and TensorFlow.js.

A Python library that implements Dilated Residual Networks, a type of convolutional neural network architecture.

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

A medical reasoning agent for chest X-ray analysis powered by AI and LLMs.

Efficient PyTorch practices for training large datasets

Codebase for a paper on efficient large-scale deep learning systems using smart algorithms over hardware acceleration.

A tutorial for using TensorFlow to build time series prediction models.

A Python library that converts videos to densepose and integrates with the MagicAnimate AI tool.

Mitsuba is a highly customizable, research-oriented renderer that provides a rich and flexible programming interface.

A smaller subset of 10 easily classified classes from Imagenet, and a little more French