# Separating personal from population gains when calibrating EEG foundation models for new users

arXiv: https://arxiv.org/abs/2609.34801 · HTML: https://mlsanity.com/paper/2609.34801/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 48 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects](https://mlsanity.com/paper/2510.21585/) (2025)
- [A Systematic Evaluation of Euclidean Alignment with Deep Learning for EEG Decoding](https://mlsanity.com/paper/2401.10746/) (2024)
- [EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models](https://mlsanity.com/paper/2601.17883/) (2026)
- [Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes](https://mlsanity.com/paper/2604.23091/) (2026)
- [NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training](https://mlsanity.com/paper/2509.26301/) (2025)
- [The Identity Trap in EEG Foundation Models: A Diagnostic Audit](https://mlsanity.com/paper/2606.06647/) (2026)
- [Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface](https://mlsanity.com/paper/2404.15350/) (2024)
- [Subject-Adaptive Transfer Learning Using Resting State EEG Signals for Cross-Subject EEG Motor Imagery Classification](https://mlsanity.com/paper/2405.19346/) (2024)
- [EEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIs](https://mlsanity.com/paper/2412.19725/) (2024)
- [Learning aligned EEG representations with subject-specific encoders](https://mlsanity.com/paper/2606.16462/) (2026)
- [Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decoding](https://mlsanity.com/paper/2607.03094/) (2026)
- [Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness](https://mlsanity.com/paper/2609.00282/) (2026)

## Abstract (arXiv)

Foundation models are increasingly adapted to individual users, but an apparent personalization gain can simply reflect a stronger population model. This distinction matters for brain-computer interfaces, where every new user must be calibrated. We evaluated personal adaptation of three frozen EEG foundation models (CBraMod, REVE and LaBraM) in 235 held-out subjects from three motor-imagery datasets, comparing each subject's adapter with the population model and with adapters fitted to other subjects. Using all first-half session labels, personal adapters improved mean balanced accuracy over the population model by 1.5-5.4 percentage points and outperformed exchanged adapters by 2.3-7.3 points in all nine model-dataset combinations. The size of this benefit depended on population training: with four times the original budget, median gains remained positive (1.0-2.0 points) but were smaller for every model, and no population model reached a confirmed plateau. Acquiring the benefit cheaply was unreliable: few-label calibration was consistently non-negative on only one dataset, and in CBraMod neither unlabeled context nor meta-learned initialization outperformed matched controls. Personalization should therefore be evaluated against both a population reference and exchanged parameters, across population-training budgets.