Trending Projects

A modular and easy-to-use Python library for training and using state-of-the-art retrieval models like ColBERT in RAG pipelines.

A Python library that quickly extracts structured Markdown notes from audio and video content.

OmniSafe is an infrastructural framework for accelerating safe reinforcement learning research.

TensorRT implementation of popular deep learning networks for efficient inference on GPUs

A collection of pre-trained AI models for the ROCK Chip AI accelerator

A Foundation Model for Generalist Gaming Agents, a powerful AI framework for building versatile gaming agents.

An open-source app that allows users to search, read, bookmark, and summarize academic papers from arXiv using AI-powered features.

Graph Transformer Architecture for developing graph neural networks with attention mechanisms.

Comprehensive roadmap to become skilled in AI, ML, data science, and more from scratch.

A Python library for reproducing the R1 Zero algorithm on logic puzzles.

A curated list of resources for developing applications using large language models (LLMs) with the Retrieval Augmented Generation (RAG) pattern.

OpenFace is a state-of-the-art tool for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments using MuJoCo.

A production-ready reinforcement learning AI agent library for building AI-powered applications.

A lightweight, self-contained Rust library for running Tensorflow and ONNX models with no dependencies

An open-source library for multilingual automatic speech recognition with word-level timestamps and confidence.

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

A workshop to understand how large language models (LLMs) are implemented and used in Python and PyTorch.

A Python library that makes it easy to visualize the activations and gradients of Keras neural networks.

A comprehensive tutorial for the LangChain library, a framework for building applications with large language models.

Deformable DETR is a state-of-the-art object detection model that uses deformable transformers for end-to-end detection.

EasyVolcap is a Python library that accelerates neural volumetric video research by providing a simple and efficient workflow.

An open-source computer vision library with thousands of pre-built algorithms and features.

A Jupyter Notebook project for measuring the accuracy of retrieval from large language models at various context lengths.

MotionDirector is a diffusion-based text-to-video generation tool focused on customizing motion for AI-generated videos.

A curated collection of LLM papers, blogs, and projects, focused on OpenAI o1 and reasoning techniques.

This repository provides examples and utilities for fine-tuning large language models (LLMs) using the PEFT library.

A curated list of efficient and compressed large language models for developers to explore.

An integrated solution for building and evaluating knowledge graphs using AI tools like GraphRAG and LightRAG.

An open-source humanoid arm for physical AI research and deployment in contact-rich environments.

A curated list of AI-powered web search tools and resources for developers and researchers.

PubLayNet is a Jupyter Notebook library for parsing and analyzing layout and structure of scientific publications.

A Java library for automatically detecting anomalies in large-scale time-series data.

A fast C++/CUDA neural network framework for high-performance deep learning and rendering.

A Rust library for interacting with the OpenAI API, enabling vibe coders to leverage AI capabilities in their projects.

Magenta is a research project exploring machine learning in art and music generation using TensorFlow.

Simple-evals is a Python library for running OpenAI's model evaluation scripts.

A Jupyter Notebook project that demonstrates sentiment analysis using LSTMs and TensorFlow.

Public facing notes page for the CS231n course on Convolutional Neural Networks.

A PyTorch implementation of the SuperGlue graph neural network for feature matching and pose estimation.

A curated collection of public EEG datasets for researchers and developers working with brain-computer interfaces.

A versatile TypeScript-based tool that transforms web content into LLM-ready data for AI/ML applications.

This is a large language model (LLM) focused on mental health, with pre/post-training, datasets, evaluation, and deployment tools.

A Python library for creating video-based multimodal explanations for LLM theorem understanding.

A curated collection of must-read papers and blogs on speculative decoding techniques for developers.

Self-Attention GAN, a Python library for generative adversarial networks using self-attention mechanisms.

A comprehensive library for hand pose estimation and tracking, useful for human-computer interaction projects.

A Jupyter Notebook repository that provides visualizations and explanations for machine learning concepts and algorithms.

SMPL-X is a Python library for working with the SMPL-X human body model.

An open-source library for automatically rigging diverse skeletons using a single neural network model.