# 🧠NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models
[Konstantinos Barmpas](https://www.barmpas.com)1,2 [Na Lee](https://www.linkedin.com/in/na-lee-57777387/)1,2 [Alexandros Koliousis](https://akoliousis.com)3
[Yannis Panagakis](http://users.uoa.gr/~yannisp/)2,4,5 [Dimitrios Adamos](https://profiles.imperial.ac.uk/d.adamos)1,2 [Nikolaos Laskaris](https://people.auth.gr/laskaris/?lang=en)2,6 [Stefanos Zafeiriou](https://profiles.imperial.ac.uk/s.zafeiriou)1,2
1Imperial College London, United Kingdom 2Cogitat, United Kingdom
3Northeastern University London, United Kingdom
4National and Kapodistrian University of Athens, Greece
5Archimedes Research Unit, Greece
6Aristotle University of Thessaloniki, Greece This is the official implementation of **NeuroRVQ**, a foundation model for biosignals powered by a state-of-the-art biosignal tokenizer
| 
| 
|
## Downstream Performance
### EEG
| Model | Motor | ERP | Memory | Sleep* | Eyes | Mean | Size |
|-----------|-------|------|---------|---------|-------|--------|-------|
| NeuroGPT | 0.682±0.083 | 0.757±0.048 | **0.597±0.029** | 0.674±0.033 | 0.827±0.036 | 0.707±0.046 | 79.5M |
| CBraMod | 0.614±0.104 | 0.777±0.052 | 0.574±0.038 | 0.635±0.041 | 0.839±0.041 | 0.688±0.055 | 4.9M |
| BIOT | 0.443±0.079 | 0.500±0.000 | 0.510±0.018 | -- | 0.763±0.049 | -- | 3.2M |
| MIRepNet | 0.689±0.086 | -- | -- | -- | -- | -- | -- |
| LaBraM | 0.630±0.076 | 0.822±0.040 | 0.526±0.026 | 0.652±0.037 | 0.799±0.047 | 0.686±0.045 | 5.8M |
| EEGPT | 0.313±0.035 | 0.668±0.146 | 0.520±0.017 | 0.634±0.044 | 0.797±0.037 | 0.587±0.056 | 25.7M |
| **NeuroRVQ** | **0.700±0.073** | **0.876±0.033** | 0.574±0.027 | **0.728±0.028** | **0.869±0.026** | **0.749±0.037** | 5.9M |
We used the benchmark presented in IEEE MLSP 2025 Paper [Assessing the Capabilities of Large Brainwave Foundation Models](https://ieeexplore.ieee.org/document/11204282).
#### About the Benchmark
Over the last decade, deep learning models have been widely used for automatic feature extraction and classification in various Brain-Computer Interface (BCI) tasks. However, their performance and generalization capabilities are often not adequately assessed, as these models are frequently trained and tested under flawed setups and / or influenced by spurious correlations. Recently, these limitations have also been observed in the training and evaluation of Large Brainwave Foundation Models (LBMs). In this work, we employ causal reasoning and careful consideration for task-discriminative artifacts in various EEG datasets covering diverse BCI paradigms and propose a benchmarking protocol to properly evaluate the decoding performance and generalization capabilities of LBMs. Utilising a subject-independent cross-validation approach for each curated benchmark dataset, we showcase that LBMs achieve marginal performance gains over conventional deep learning baselines.
[Open-Source Benchmark Code](https://github.com/dykestra/EEG-Benchmarking)
## Installation
```bash
conda create -n neurorvq python=3.10
conda activate neurorvq
# Install requirements
pip install -r requirements.txt
```
## Download Models
The models and the sample biosignal for reconstruction demos can be downloaded manually from [HuggingFace]() or using python:
```python
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="ntinosbarmpas/NeuroRVQ", filename="pretrained_models/tokenizers/NeuroRVQ_EEG_tokenizer_v1.pt", local_dir="./")
hf_hub_download(repo_id="ntinosbarmpas/NeuroRVQ", filename="pretrained_models/foundation_models/NeuroRVQ_EEG_foundation_model_v1.pt", local_dir="./")
hf_hub_download(repo_id="ntinosbarmpas/NeuroRVQ", filename="example_files/eeg_sample/example_eeg_file.xdf", local_dir="./")
```
## Model Loading / Usage
Load tokenizer and see reconstruction results. Example for EEG tokenizer:
```python
from inference.run.NeuroRVQ_EEG_tokenizer_example import load_neurorqv_tokenizer
# Set run_example=True and plot_results=True to see reconstruction results
# Checkout the load_neurorqv_tokenizer() function to load and use tokenizer
load_neurorqv_tokenizer(run_example=True, plot_results=True, verbose=True,
model_path='./pretrained_models/tokenizers/NeuroRVQ_EEG_tokenizer_v1.pt')
```
Load foundation model and see an example for fine-tuning. Example for EEG foundation model:
```python
from inference.run.NeuroRVQ_EEG_FM_example import load_neurorqv_fm
# Checkout the load_neurorqv_fm() function with fine_tuning=False to see the correct model loading
# See the instructions in data.py for your custom dataset before setting fine_tuning=True
load_neurorqv_fm(fine_tuning=False, verbose=True,
model_path = './pretrained_models/foundation_models/NeuroRVQ_EEG_foundation_model_v1.pt')
```
## Citation
```
@misc{neurorvq,
title={NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models},
author={Konstantinos Barmpas and Na Lee and Alexandros Koliousis and Yannis Panagakis and Dimitrios A. Adamos and Nikolaos Laskaris and Stefanos Zafeiriou},
year={2025},
eprint={2510.13068},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2510.13068},
}
```