🚀 Lightning-fast computer vision models. Fine-tune SOTA models with just a few lines of code. Ready for cloud ☁️ and edge 📱 deployment.

CIFNet: A lightweight, single-pass Class Incremental Learning model designed for edge devices. Minimizes training time, energy consumption, and memory usage, making it ideal for real-time, resource-constrained environments.

🧠 Official implementation of FedHENet: A frugal, one-shot federated learning framework for heterogeneous environments. Privacy-preserving via HE, energy-efficient, and hyperparameter-free. Accepted at ESANN 2026.

This repository contains the code and data of the paper titled "FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution."

PyTorch implementation of the "Reducing inference energy consumption using dual complementary CNNs" paper published in FGCS journal.

Maximizing LLM tokens/sec on Jetson under limited memory

This repository contains the PyTorch implementation of the paper "Selecting Images With Entropy For Frugal Knowledge Distillation'" published in IEEE Access.

A curated collection of Edge AI courses for everyone

An open and practical guide to Edge Language

A production-ready, frugal, sovereign AI system that orchestrates India's open-source language models to achieve state-of-the-art reasoning on consumer hardware through Test-Time Compute (TTC) and Cognitive Serialization.

An open and practical guide to Edge Audio.