Thorir Mar Ingolfsson

Making AI run on microwatts

Thorir Mar Ingolfsson · Postdoctoral Researcher · ETH Zürich

I bridge large-scale pre-training and ultra-low-power hardware so that wearable biomedical devices can analyze EEG, ECG, and other biosignals in real time: on the device, not in the cloud.

Explore my research Work with me → Download CV
News
Jul 2026VitalFM funded by the Swiss AI Initiative (Large Grant, 400k GPU hours on Alps): a unified foundation model for physiological waveforms, from Alps to edge.
Jul 2026Awarded a Hasler Foundation grant (CHF 50,000) for quantized recursive inference on resource-constrained edge AI.
Jun 20262nd place at the ETH Zürich Probabilistic Computing Hackathon with Thermo-TRM.
Jun 2026New preprint: LuMamba brings LeJEPA to biosignals — 377× cheaper than LaBraM.
Sep 2025LUNA accepted at NeurIPS 2025 — topology-agnostic EEG foundation model, 300× fewer FLOPs.
1080 Citations Google Scholar
14 h-index Core research impact
22 Publications View publications →

Three questions, one goal

How do we make machine learning clinically useful on devices that run for weeks on a coin cell? My work attacks this from three directions.

Foundation models for biosignals

Pre-trained models that understand EEG and other biosignals across devices, montages, and tasks, with minimal fine-tuning.

LUNA · NeurIPS 2025 · 300× fewer FLOPs, SOTA on TUAR, any electrode layout.
Explore this direction →

Tiny recursion models

Deep supervision and adaptive-depth recursion for time series: sophisticated temporal reasoning inside microcontroller budgets.

Thermo-TRM · recursion as annealed sampling; 2nd place, ETH Probabilistic Computing Hackathon.
Explore this direction →

Ultra-low-power deployment

Hardware and algorithm co-design that puts clinical-grade models on GAP9 and RISC-V wearables at microwatt power.

Seizure detection & BMI · real-time, on-device, battery-week lifetimes.
Explore this direction →
Flagship software

BioFoundation

★ 121 stars⑂ 15 forksApache 2.0

The open-source home of our biosignal foundation-model family. PyTorch Lightning, Hydra configs, pre-trained weights on Hugging Face, and distributed training: everything needed to pre-train, fine-tune, and deploy.

View on GitHub Weights on Hugging Face →
LUNA logoLUNA
Topology-agnostic transformer · 300× fewer FLOPsNeurIPS 2025
FEMBA logoFEMBA
Bidirectional Mamba · linear-time, 0.949 AUROCEMBC 2025
LuMamba logoLuMamba
LUNA + FEMBA + LeJEPA · 377× cheaper than LaBraMarXiv 2026
TinyMyo logoTinyMyo
3.6M-param EMG model for microcontrollersarXiv 2025
CBCEReBrO
Compact encoder · alternating attentionarXiv 2025
Work with me

Open MSc & semester projects at ETH Zürich

I supervise students on tiny recursive models for time series and quantized TRMs on edge hardware — real hardware, weekly supervision, and a paper-shaped goal from day one. Recent student work landed at NeurIPS, EMBC, and IEEE journals.

Work with me → Open topics & how it works

Recent Posts

Thermo-TRM: Recursive Reasoning at Thermodynamic Prices
At the ETH Zurich Probabilistic Computing Hackathon I reframed the recursion in TRM/PTRM/GRAM as annealed sampling on an energy-based model, ran the whole loop on Extropic’s THRML simulator, and solved the hardest known Sudoku as a ground-state problem. The recursion buys roughly 7x fewer sampling sweeps, and when the network is confidently wrong the physics rescues it. It won 2nd place.
Thorir Mar Ingolfsson
Last updated on 25 Jun 2026 8 min read
Project
Thermo-TRM: Recursive Reasoning at Thermodynamic Prices
LuMamba: How the Pre-training Objective Shapes an EEG Foundation Model
We bring LeJEPA to biosignals for the first time and show that the choice of self-supervised objective (masked reconstruction, LeJEPA, or a mix) trades latent-space structure for cross-montage generalisation, all on a 4.6M-parameter bi-Mamba model that is 377× cheaper than LaBraM.
Thorir Mar Ingolfsson, Danaé Broustail
Last updated on 15 Jun 2026 10 min read
Project
LuMamba: How the Pre-training Objective Shapes an EEG Foundation Model
LUNA: An EEG Foundation Model That Doesn't Care How Many Electrodes You Have
How learned queries and cross-attention let LUNA decouple compute from electrode count, cutting FLOPs by 300× and GPU memory by 10× while still hitting state-of-the-art on TUAR.
Thorir Mar Ingolfsson
Last updated on 7 May 2026 8 min read
Project
LUNA: An EEG Foundation Model That Doesn't Care How Many Electrodes You Have
See all posts

Recent Publications

Tip: Explore the full archive and filter by venue, topic, or year on the publications page.
Bálint Tóth, Dominik Senti, Thorir Mar Ingolfsson, Jeffrey Zweidler, Alexandre Elsig, Luca Benini, Yawei Li (2025). Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation. In EMBC 2025.

PDF Project DOI

Jonathan Dan, Una Pale, Alireza Amirshahi, William Cappelletti, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Adriano Bernini, Luca Benini, Sándor Beniczky, David Atienza, Philippe Ryvlin (2025). SzCORE: Seizure Community Open-Source Research Evaluation Framework for EEG-Based Seizure Detection. In Epilepsia 66 (Suppl. 3).

PDF Code DOI (Epilepsia)

Thorir Mar Ingolfsson, Victor Javier Kartsch, Luca Benini, Andrea Cossettini (2025). A Wearable Ultra-Low-Power System for EEG-Based Speech-Imagery Interfaces. In IEEE TBioCAS 2025.

IEEE Xplore

Alexandru Dimofte, Glenn Anta Bucagu, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Luca Benini, Yawei Li (2025). CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention. arXiv:2501.10885 (2025).

PDF Project DOI

Lan Mei, Cristian Cioflan, Thorir Mar Ingolfsson, Victor Kartsch, Andrea Cossettini, Xiaying Wang, Luca Benini (2024). Train-On-Request: An On-Device Continual Learning Workflow for Adaptive Real-World Brain-Machine Interfaces. In IEEE BioCAS 2024.

PDF Code DOI

See all publications

Contact