Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
Alexander Gräfe, Ding Huo, Vincent de Bakker +3
Transformer models are rapidly becoming a cornerstone of modern Internet of Things (IoT) applications, yet their computational and memory demands far exceed the capabilities of a s…
cs.LG2025
MPX: Mixed Precision Training for JAX
Alexander Gräfe, Sebastian Trimpe
Mixed-precision training has emerged as an indispensable tool for enhancing the efficiency of neural network training in recent years. Concurrently, JAX has grown in popularity as…
cs.LG2025
RockNet: Distributed Learning on Ultra-Low-Power Devices
Alexander Gräfe, Fabian Mager, Marco Zimmerling +1
As Machine Learning (ML) becomes integral to Cyber-Physical Systems (CPS), there is growing interest in shifting training from traditional cloud-based to on-device processing (Tiny…