activity
20242026
collaborators

6 papers

cs.LG2026

Efficient Zeroth-Order Federated Finetuning of Language Models on Resource-Constrained Devices

Mohamed Aboelenien Ahmed, Kilian Pfeiffer, Ramin Khalili +2

Federated Learning (FL) is a promising paradigm for finetuning Large Language Models (LLMs) across distributed data sources while preserving data privacy. However, finetuning such…

cs.AR2026

Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition

José Juan Hernández Morales, Georgios Mentzos, Frank Hannig +4

The paradigm shift towards local and on-device inference under stringent resource constraints is represented by the tiny machine learning (TinyML) domain. The primary goal of TinyM…

cs.LG2025

TransAxx: Efficient Transformers with Approximate Computing

Dimitrios Danopoulos, Georgios Zervakis, Dimitrios Soudris +1

Vision Transformer (ViT) models which were recently introduced by the transformer architecture have shown to be very competitive and often become a popular alternative to Convoluti…

cs.LG2025

Efficient Federated Finetuning of Tiny Transformers with Resource-Constrained Devices

Kilian Pfeiffer, Mohamed Aboelenien Ahmed, Ramin Khalili +1

In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require m…

cs.LG2025

Accelerated Training on Low-Power Edge Devices

Mohamed Aboelenien Ahmed, Kilian Pfeiffer, Heba Khdr +3

Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level…

cs.AR2024

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

Kilian Pfeiffer, Konstantinos Balaskas, Kostas Siozios +1

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do…