Published June 2, 2026 | Version v0.6.0
Software Open

Open EEG Bench: Benchmarking parameter-efficient fine-tuning of EEG foundation models

Authors/Creators

  • 1. Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands
  • 2. Yneuro, Paris, France; University of California San Diego, USA
  • 3. University of California San Diego, USA
  • 4. INRIA, France
  • 5. Swartz Center for Computational Neuroscience, Institute for Neural Computation, San Diego Supercomputer Center, University of California San Diego, USA; CNRS, France

Description

Open EEG Bench is a Python library for evaluating EEG foundation models across 12 pre-windowed neuroscience datasets and 8 fine-tuning strategies (frozen linear probing, ridge probing, LoRA, IA3, AdaLoRA, DoRA, OFT, full fine-tuning, and two-stage training). A single benchmark() call produces a comparable, reproducible evaluation suitable for local or SLURM-cluster execution.

Notes

If you use Open EEG Bench in your research, please cite it using the metadata below.

Files

braindecode/OpenEEGBench-v0.6.0.zip

Files (479.3 kB)

Name Size Download all
md5:e642eeccbc67fd0d1f5b5f46905ed066
479.3 kB Preview Download

Additional details

Related works

Is supplement to
Software: https://github.com/braindecode/OpenEEGBench/tree/v0.6.0 (URL)

Software

Repository URL
https://github.com/braindecode/OpenEEGBench