# Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning

arXiv: https://arxiv.org/abs/2507.01196 · HTML: https://mlsanity.com/paper/2507.01196/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [4M: Massively Multimodal Masked Modeling](https://mlsanity.com/paper/2312.06647/) (2023)
- [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting](https://mlsanity.com/paper/2405.10216/) (2024)

## Built on by (most cited first, 15 of 15)

- [EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models](https://mlsanity.com/paper/2508.17742/) (2025)
- [Neural Codecs as Biosignal Tokenizers](https://mlsanity.com/paper/2510.09095/) (2025)
- [DeeperBrain: A Neuro-Grounded EEG Foundation Model Towards Universal BCI](https://mlsanity.com/paper/2601.06134/) (2026)
- [MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training](https://mlsanity.com/paper/2602.02494/) (2026)
- [Mitigating Subject Dependency in EEG Decoding with Subject-Specific Low-Rank Adapters](https://mlsanity.com/paper/2510.08059/) (2025)
- [Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models](https://mlsanity.com/paper/2605.17562/) (2026)
- [EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models](https://mlsanity.com/paper/2605.26910/) (2026)
- [SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels](https://mlsanity.com/paper/2602.17251/) (2026)
- [A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models](https://mlsanity.com/paper/2605.28563/) (2026)
- [A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG](https://mlsanity.com/paper/2510.07960/) (2025)
- [BrainDistill: Implantable Motor Decoding with Task-Specific Knowledge Distillation](https://mlsanity.com/paper/2601.17625/) (2026)
- [DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models](https://mlsanity.com/paper/2604.15016/) (2026)
- [Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding](https://mlsanity.com/paper/2605.00857/) (2026)
- [Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction](https://mlsanity.com/paper/2609.22105/) (2026)
- [Neuron-Level Architecture Growth: A Controlled Evaluation for EEG Time-Series Decoding](https://mlsanity.com/paper/2609.33880/) (2026)

## Abstract (arXiv)

Foundation Models have demonstrated significant success across various domains in Artificial Intelligence (AI), yet their capabilities for brainwave modeling remain unclear. In this paper, we comprehensively evaluate current Large Brainwave Foundation Models (LBMs) through systematic fine-tuning experiments across multiple Brain-Computer Interface (BCI) benchmark tasks, including memory tasks and sleep stage classification. Our extensive analysis shows that state-of-the-art LBMs achieve only marginal improvements (0.9%-1.2%) over traditional deep architectures while requiring significantly more parameters (millions vs thousands), raising important questions about their efficiency and applicability in BCI contexts. Moreover, through detailed ablation studies and Low-Rank Adaptation (LoRA), we significantly reduce trainable parameters without performance degradation, while demonstrating that architectural and training inefficiencies limit LBMs' current capabilities. Our experiments span both full model fine-tuning and parameter-efficient adaptation techniques, providing insights into optimal training strategies for BCI applications. We pioneer the application of LoRA to LBMs, revealing that performance benefits generally emerge when adapting multiple neural network components simultaneously. These findings highlight the critical need for domain-specific development strategies to advance LBMs, suggesting that current architectures may require redesign to fully leverage the potential of foundation models in brainwave analysis.