Trending Projects

This repository contains scripts, models, and files for the Deep Noise Suppression (DNS) Challenge, a tool for developers working with audio processing and AI.

Official PyTorch implementation of a framework for learning to adapt models at test time.

Official implementation of HierSpeech++, a hierarchical speech recognition model.

A redundancy-aware KV cache compression library for improving reasoning model performance.

A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search and OpenAI for chat and Q&A.

a security scanner for custom LLM applications

A public repository for exploring LLM-driven data engineering concepts and tools.

Rotary Transformer, a Python library for Transformer models that incorporates rotary position encoding.

A Python-based tool to easily generate thousands of 3D models, images, and animation for NFTs using Blender.

A curated list of papers and resources on neural radiance fields (NeRF), a powerful technique for 3D scene representation.

A curated list of must-read papers on recommender systems, covering collaborative filtering, deep learning, and more.

An open-source AI tool that converts landscape photos and videos into anime-style art.

A Python library that provides a simple wrapper for hyperparameter optimization using Keras and Hyperopt.

A Python library for Genetic Programming with a scikit-learn inspired API for developers building AI tools.

Brevitas is a PyTorch library for neural network quantization, enabling efficient hardware acceleration on FPGAs and other devices.

Mip-Splatting is a novel 3D Gaussian splatting algorithm for alias-free novel view synthesis.

An open-source AI agent that interacts with graphical user interfaces using natural language

An evolutionary algorithm library in Python for developers interested in AI and machine learning.

A Python library for evaluating multi-object tracking algorithms using HOTA and other metrics.

A general object foundation model for computer vision tasks in images and videos at scale

Collection of Chinese safety prompts for evaluating and improving the safety of large language models (LLMs).

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

Lightweight implementation of conformal prediction, a method for uncertainty estimation in machine learning.

A Python library that empowers developers to build applications and systems with self-contained computer vision capabilities.

A probabilistic programming library powered by NumPy and JAX for Bayesian inference and MCMC sampling.

Contrastive unpaired image-to-image translation library using PyTorch, with faster and lighter training than CycleGAN.

Open-source Python library for feature engineering and selection, compatible with scikit-learn.

A PyTorch-based AI factory that enables easy configuration and running of complex AI recipes across various data domains.

Official implementation of the RAVE model, a Realtime Audio Variational autoEncoder for generative audio AI.

Demo of in-browser Fast Neural Style Transfer with deeplearn.js library

A C-based toolkit for deploying AI models on Rockchip AI accelerated hardware.

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

An open-source PyTorch implementation of Video Frame Interpolation via Adaptive Separable Convolution.

A TensorFlow implementation of a scalable distributed deep reinforcement learning framework.

An open-source library providing GPT-powered tools and APIs for building AI-powered applications.

A curated list of open-source alternatives to the popular AI chatbot ChatGPT.

A collection of Python notebooks with machine learning and deep learning examples using the Azure ML SDK.

A PyTorch-based computer vision foundation model with deformable convolutions for object detection and segmentation.

Easily compute CLIP embeddings and build a CLIP-based retrieval system with this Jupyter Notebook library.

A curated list of open-source models, datasets, and benchmarks for domain-specific language models.

PyTorch implementation of the Squeeze-and-Excitation Network (SENet) architecture for deep learning models.

A hybrid A* path planner for the KTH Research Concept Vehicle, focused on robotics and motion planning.

A fast implementation of Mixture of Experts (MoE) for PyTorch, enabling efficient large-scale neural networks.

A single-document unsupervised keyword extraction tool focused on AI and machine learning use cases.

A curated collection of top 200 deep learning GitHub repositories sorted by stars for AI developers.

SpeechGPT is a Python library for building speech-based applications using large language models.

A curated list of must-read papers on knowledge editing for large language models.

A powerful and extensible machine learning framework for hackers and AI enthusiasts, built in Rust.

A Python-based tool for detecting and mitigating phishing attacks on social media using LLM-based modeling.

A reinforcement learning environment for developing AI agents that can play the Google Research Football game.