Eón es un manifiesto de software que demuestra que la Inteligencia no es Artificial, es un fenómeno descubierto (Reservoir Computing en el Borde), no un producto de la fuerza bruta. Rompemos con el paradigma de la computación masiva: Eón ejecuta un núcleo neuronal complejo con un uso de memoria de solo 1.3 KB en entornos de bajo consumo (IoT).

🎓 Automatically Update Some Fields Papers Daily using Github Actions (Update Every 12th hours)

NetFL is a framework for running Federated Learning (FL) experiments in simulated IoT and Fog/Edge computing environments, with support for heterogeneous devices and configurable network conditions.

Flower: A Friendly Federated AI Framework

NVIDIA Federated Learning Application Runtime Environment

A flexible, modular, and easy to use library to facilitate federated learning research and development in healthcare settings

Distributed differentiable graph computation using PyTensor

[ICML 2025] The Official implementation of our paper "Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off"

A benchmarking framework for decentralized optimization

Federated Learning (FL) experiment simulation in Python.

Top-1 compression suffices for federated unlearning with the help of adaptive error feedback

Track Federated Learning Papers

Source code for the paper "Joint Class-Balanced Client Selection and Bandwidth Allocation for Cost-Efficient Federated Learning in Mobile Edge Computing Networks". This paper is pulished in IEEE TMC.

✨✨A curated list of latest advances on Large Foundation Models with Federated Learning

Federated data Preprocessing via aggregated Statistics

A complete federated learning system for training RAG (Retrieval-Augmented Generation) models across multiple organizations while keeping data private.

A secure, scalable, and modular implementation of a Federated Learning system designed for distributed environments. Built using Python, PyTorch, gRPC, and Consul, this project enables multiple clients to collaboratively train machine learning models while ensuring data privacy and dynamic service discovery.

A Federated Learning Experimenting Tool to Measure Fault Tolerance to Byzantine Clients