Trending Projects

PoolFormer is a vision transformer model that achieves state-of-the-art performance on image classification tasks.

A Python library that turns any face into a video game character, pixel art, claymation, 3D, or toy using generative AI models.

An open-source library for learning continuous image representation using local implicit image function.

Properly implemented ResNet-s for CIFAR10/100 in PyTorch, matching the original paper description.

A unified deep learning model for correspondence, stereo, and depth estimation tasks.

Demonstrations of Magenta Models, a set of open-source machine learning models for music and art generation.

Realtime head pose estimation using ONNX and OpenCV for computer vision and AI applications.

A PyTorch library for training generative adversarial transformer models for image generation.

This is an LLVM-based code obfuscation framework maintained by the Cryptography and Computer Security Lab at Shanghai Jiao Tong University.

A Python library for 3D human avatar reconstruction from videos using self-supervised scene decomposition.

A Python library for unsupervised time series anomaly detection, useful for data science and ML applications.

A tool that helps developers easily share ChatGPT Plus/Claude Pro services with their peers.

PyTorch implementation of state-of-the-art reinforcement learning algorithms for vibe coders.

A simple local voice assistant powered by Whisper and large language models.

Zero-shot image restoration using a denoising diffusion model that can remove various types of noise and artifacts.

A TypeScript library that provides a cheap API to access ChatGPT 4o, GPT-5, and Claude-4 models

The Simple Agent Development Kit for building AI-powered software agents and bots.

A Python library for video recognition using deep feature flow and other computer vision techniques.

Minimal Deep Q Learning (DQN & DDQN) implementations in Python using the Keras library for reinforcement learning.

Differentiable data augmentation techniques for efficient training of generative adversarial networks (GANs).

MovieLens based recommender system for developers interested in building recommendation engines.

Real-time object recognition app built with TensorFlow and OpenCV for computer vision tasks.

A zero-shot image editing tool that allows users to transfer textures and styles from reference images.

This Python tool accelerates the download of HuggingFace models from mirror sites for faster model training and deployment.

MLOps tool for building and deploying machine learning models on Azure cloud services

A Python library for learning graph embeddings and applying them to tasks like link prediction.

A machine learning library for transportation data imputation and prediction.

A collection of pre-trained StyleGAN 2 models for AI-powered generative art and image synthesis.

A high-performance and accurate license plate detection library built using Yolov5 and ncnn.

A repository containing documents used by the TensorFlow developer community.

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

VideoLLaMA 2 is a Python library that advances spatial-temporal modeling and audio understanding in video-based large language models.

A PyTorch library for monocular depth estimation using deep learning techniques.

A hands-on guide to deep reinforcement learning using Python and popular frameworks like OpenAI Gym.

A deep learning model for removing watermarks and overlays from images, useful for vibe coders working with AI-generated content.

A collection of basic examples for learning and experimenting with Reinforcement Learning in Python.

Open-source notebooks for music information retrieval research and education.

A visualization toolbox for LSTM neural networks, useful for developers working with AI/ML models.

A Python package to run contextualized topic modeling, combining BERT embeddings and topic models.

An intelligent question-answering system based on a pharmaceutical knowledge graph.

A tool for visualizing attention in deep learning models, useful for AI developers building with AI tools.

Optimizes numerical and discrete search spaces with various gradient-free optimization techniques.

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

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

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

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

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

Mulberry is an o1-like Reasoning and Reflection MLLM implemented via Collective MCTS for AI-powered coding tools.

This is a deprecated SDK for the Google GenAI platform, which provides tools for AI-powered coding and development.

A research project focused on learning latent dynamics for planning from pixel-based observations.