Quantization

FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-Low Power Microcontroller
Physiologically-aware pre-training and INT8 deployment of a bidirectional Mamba EEG foundation model on a microcontroller.
Anna Tegon, Nicholas Lehmann, Yawei Li, Andrea Cossettini, Luca Benini, Thorir Mar Ingolfsson
PDF Project DOI
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-Low Power Microcontroller
AMLD Intelligence Summit 2026 – Pushing Biosignal FMs to the Edge
Poster presentation of our full-stack framework for deploying biosignal foundation models on ultra-low-power edge devices at AMLD 2026 in Lausanne.
10 Feb 2026 SwissTech Convention Center, EPFL, Lausanne, Switzerland
PDF Code AMLD 2026 event page
AMLD Intelligence Summit 2026 – Pushing Biosignal FMs to the Edge
IEEE EMBC 2025 – Silent Disco Presentations
Presented quantized biosignal foundation models in EMBC’s silent disco session while Anna Tegon delivered FEMBA.
17 Jul 2025 11:00 Bella Center Copenhagen, Denmark
Code Blood-pressure slides FEMBA slides Finetuning & Quantization paper FEMBA paper
IEEE EMBC 2025 – Silent Disco Presentations
Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation
Transfers EEG foundation models to ECG/PPG for BP estimation, reaching 1.57 mmHg MAE with 3.5× model compression via INT8 quantization.
Bálint Tóth, Dominik Senti, Thorir Mar Ingolfsson, Jeffrey Zweidler, Alexandre Elsig, Luca Benini, Yawei Li
PDF Project DOI
Quantized Tiny Recursive Models for Edge Deployment
Quantize TRMs to low precision and deploy them on GAP9 or Cortex-M, exploring accuracy–energy trade-offs and adaptive compute.
Last updated on 5 Jul 2026 MSc Thesis