Trending Projects

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

Open Images is a large dataset of annotated images for computer vision and machine learning research.

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

A scalable multi-agent reinforcement learning simulator for autonomous driving research and development.

A fast and simple face swap extension node for the ComfyUI AI tool, built using Python.

This project is a deformation inpainting network for realistic face visually dubbing on high resolution video.

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

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

MixGRPO is a Python library that unlocks flow-based GRPO efficiency with mixed ODE-SDE for diffusion and reinforcement learning.

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 C++ library for building machine learning applications, revitalizing C++ as a ML front-end.

A Chinese medical consultation large language model for healthcare professionals and researchers.

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

A Python library for verifying mathematical proofs using natural language processing.

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

Official PyTorch implementation of a scalable transformer-based generative model for image generation and manipulation.

A starter agent that can solve a number of OpenAI Universe environments, useful for AI and ML developers.

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

Resources for phase recovery, a computational imaging technique using deep learning and interferometry.

Official implementation of a paper on watermarking images with localized messages for AI-assisted image editing.

A fast and robust feature matching library for computer vision tasks like SfM and SLAM.

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

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

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

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

A novel method for zero-shot text-driven generation and animation of 3D avatars using CLIP and NeRF.

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

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

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

A collection of resources and code samples for semantic segmentation using deep learning models.

Efficient PyTorch practices for training large datasets

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

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

A benchmarking tool for measuring performance of deep learning operations on different hardware.

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

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

A curated list of 99 machine learning projects for anyone interested in learning and building with ML

Unofficial PyTorch implementation of the Conformer model for speech recognition tasks.

Applications based on Wi-Fi CSI (Channel state information) for indoor positioning and human detection.

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

LongBench is a benchmark for evaluating large language models on long-context tasks.

Relation Networks for object detection, a Python library for computer vision tasks.

An open-source PyTorch library for training Generative Adversarial Networks (GANs) with spectral normalization and projection discriminators.

A Python benchmark suite for evaluating text-to-3D generation models and techniques.

A curated list of causal inference libraries, resources, and applications for developers.

A bio-computing platform for large-scale representation learning and multi-task deep learning on molecular and biological data.

OpenGV is a collection of computer vision methods for solving geometric vision problems.

PyTorch re-implementation of DeepLab v2 for semantic segmentation on COCO-Stuff and PASCAL VOC datasets.

A PyTorch implementation of a generative adversarial network for learning cross-domain relations.

A large multimodal multilingual dataset of image-text pairs from Wikipedia for machine learning research.