Trending Projects

A large-scale LLM inference engine built in C++ with support for various AI hardware accelerators.

A collection of machine learning algorithms for edge devices developed by Microsoft Research India.

A curated collection of high-quality information sources in the AI technology domain.

A modular full-stack reinforcement learning library for large language models (LLMs).

This is a Python library for learning to act by watching unlabeled online videos using Video PreTraining (VPT).

This is a Python library for learning flow fields in attention for controllable person image generation.

A Python-based agent that uses speech recognition and text-to-speech to enable conversational interactions via WhatsApp.

Open-source code for the ProteinMPNN paper, a machine learning model for protein structure prediction.

ModernBERT brings the BERT language model into the modern era with architecture changes and scaling.

This GitHub repository provides a collection of tools for controllable video and image generation, including AI-powered animation and ControlNeXt.

An open-source e-book on building applications with large language models (LLMs), including prompt engineering, architecture design, and more.

Examples for using ONNX Runtime for machine learning inferencing.

An official repository for a paper on using executable code actions to elicit better LLM agents

A Python library for developers building AI-powered applications and tools.

An open-source Python library that uses invisible watermarking to protect creators' intellectual property

A Julia framework for acausal modeling, symbolic math, and parallelized scientific machine learning.

A Python library for generating physically stable 3D toy brick models from text prompts.

The official implementation of RAPTOR, a framework for Recursive Abstractive Processing for Tree-Organized Retrieval.

DomainBed is a suite to test domain generalization algorithms for machine learning models.

A simple Python implementation of a GRPO-like LLM for reproducing r1-like thinking.

A curated list of papers, tutorials, and surveys on AI for time series analysis and forecasting.

An all-in-one LLMs chat UI for Apple Silicon Macs using the MLX framework, built with Python.

An open-source Java and Kotlin solver library for optimizing scheduling and routing problems using AI.

A high-level deep learning framework written in Kotlin and inspired by Keras.

A Python library that uses LLMs and embeddings to process datasets with up to 1000x speedups

Official implementation of Rectified Flow, a novel AI model architecture with impressive performance.

A Python library for 3D reconstruction and tracking of humans using transformer models.

A Python library for training and deploying image-based captcha recognition models.

A Python library that provides a wrapper for the ComfyUI AI-powered video generation tool.

A powerful benchmark for Monte Carlo Tree Search in sequential decision-making scenarios.

A deep-dive on the entire history of deep-learning, useful for developers interested in AI and machine learning.

A curated list of Diffusion Model in RL resources for developers working with AI tools.

A large language model framework for reasoning in a continuous latent space.

LiteRT is Google's on-device framework for high-performance ML & GenAI deployment on edge platforms.

A Python library for building AI-powered agent-based systems, with a focus on automated design and optimization.

Voyager is an interactive RGBD video generation model that supports real-time 3D reconstruction from camera input.

TypeScript/JavaScript SDK for Gemini and Vertex AI, enabling developers to build AI-powered applications.

A PyTorch implementation of Federated Learning, a distributed machine learning technique.

This repository provides implementations of different architectures for emotion recognition in conversations.

A symbolic programming library for high-performance, parallel, and symbolic computing in Julia.

A fork to add multimodal model training capabilities to the open-r1 project, a framework for building AI tools.

The KDL document language specifications - a serialization format for vibe coders using AI tools.

Code repository for a book on feature engineering for machine learning

An open-source project exploring advanced Retrieval-Augmented Generation systems with AI LLM agents.

A Python library that provides a data engine for empowering embodied AI using world models.

The VS Code Jupyter extension provides a powerful interface for data science and machine learning workflows in VS Code.

This repository contains the source code for a tool to analyze the real context size of long-context language models.

A Python library that provides native multimodal models for building world-learning AI systems.

An open-source library for constructing vectorized high-definition maps for autonomous driving in real-time

A Jupyter Notebook project for de-pixelating a YouTube video.