# Tokenizing Single-Channel EEG with Time-Frequency Motif Learning

arXiv: https://arxiv.org/abs/2502.16060 · HTML: https://mlsanity.com/paper/2502.16060/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks](https://mlsanity.com/paper/1901.06523/) (2019)
- [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)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://mlsanity.com/paper/2202.01381/) (2022)
- [Transformer-based Spatial-Temporal Feature Learning for EEG Decoding](https://mlsanity.com/paper/2106.11170/) (2021)
- [Tokenization Is More Than Compression](https://mlsanity.com/paper/2402.18376/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG](https://mlsanity.com/paper/2208.02405/) (2022)
- [EEG2Rep: Enhancing Self-supervised EEG Representation Through Informative Masked Inputs](https://mlsanity.com/paper/2402.17772/) (2024)
- [Fredformer: Frequency Debiased Transformer for Time Series Forecasting](https://mlsanity.com/paper/2406.09009/) (2024)
- [Improved EEG Event Classification Using Differential Energy](https://mlsanity.com/paper/1801.02477/) (2018)
- [The Foundations of Tokenization: Statistical and Computational Concerns](https://mlsanity.com/paper/2407.11606/) (2024)
- [REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning](https://mlsanity.com/paper/2311.00519/) (2023)
- [Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding](https://mlsanity.com/paper/1705.08006/) (2017)
- [EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer](https://mlsanity.com/paper/2405.02165/) (2024)
- [Motiflets -- Simple and Accurate Detection of Motifs in Time Series](https://mlsanity.com/paper/2206.03735/) (2022)
- [Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder](https://mlsanity.com/paper/2402.17433/) (2024)
- [Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers](https://mlsanity.com/paper/2208.06991/) (2022)
- [Automated Sleep Staging via Parallel Frequency-Cut Attention](https://mlsanity.com/paper/2204.03173/) (2022)
- [Defining Fundamental Frequency for Almost Harmonic Signals](https://mlsanity.com/paper/2003.10767/) (2020)
- [Multi-Tier Platform for Cognizing Massive Electroencephalogram](https://mlsanity.com/paper/2204.09840/) (2022)
- [Multivariate Temporal Dictionary Learning for EEG](https://mlsanity.com/paper/1303.0742/) (2013)

## Built on by (most cited first, 17 of 17)

- [CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model](https://mlsanity.com/paper/2506.09110/) (2025)
- [ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks](https://mlsanity.com/paper/2602.23285/) (2026)
- [Integrating Biological and Machine Intelligence: Attention Mechanisms in Brain-Computer Interfaces](https://mlsanity.com/paper/2502.19281/) (2025)
- [A Systematic Evaluation of Sample-Level Tokenization Strategies for MEG Foundation Models](https://mlsanity.com/paper/2602.16626/) (2026)
- [SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding](https://mlsanity.com/paper/2603.16739/) (2026)
- [Making Conformal Predictors Robust in Healthcare Settings: a Case Study on EEG Classification](https://mlsanity.com/paper/2602.19483/) (2026)
- [Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts](https://mlsanity.com/paper/2604.16926/) (2026)
- [Context-aware tokenization for Cross-subject Emotion Decoding from EEG](https://mlsanity.com/paper/2606.00884/) (2026)
- [Channel-Preserving Representation Alignment for EEG-to-Music Reconstruction](https://mlsanity.com/paper/2606.04040/) (2026)
- [Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes](https://mlsanity.com/paper/2607.22508/) (2026)
- [EEGForceFusion: Joint Tokenised-Continuous Representation Learning for Subject-Independent Grasp Force Decoding](https://mlsanity.com/paper/2607.24126/) (2026)
- [Continuous-Latent Predictive Modeling with Semantic Alignment for EEG-Language Foundation Models](https://mlsanity.com/paper/2608.11656/) (2026)
- [A Roadmap for MEG Foundation Models](https://mlsanity.com/paper/2609.04461/) (2026)
- [GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling](https://mlsanity.com/paper/2609.37934/) (2026)
- [SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction](https://mlsanity.com/paper/2610.10571/) (2026)
- [DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models](https://mlsanity.com/paper/2610.14497/) (2026)
- [NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection](https://mlsanity.com/paper/2610.20349/) (2026)

## Abstract (arXiv)

Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from single-channel EEG signals and encodes them into discrete tokens. We propose a dual-path architecture with time-frequency masking to capture robust motif representations, and it is model-agnostic, supporting both lightweight transformers and existing foundation models for downstream tasks. Our study demonstrates three key benefits: Accuracy: Experiments on four diverse EEG benchmarks demonstrate consistent performance gains across both single- and multi-dataset pretraining settings, achieving up to 11% improvement in Cohen's Kappa over strong baselines. Generalization: Moreover, as a plug-and-play component, it consistently boosts the performance of diverse foundation models, including BIOT and LaBraM. Scalability: By operating at the single-channel level rather than relying on the strict 10-20 EEG system, our method has the potential to be device-agnostic. Experiments on ear-EEG sleep staging, which differs from the pretraining data in signal format, channel configuration, recording device, and task, show that our tokenizer outperforms baselines by 14%. A comprehensive token analysis reveals strong class-discriminative, frequency-aware, and consistent structure, enabling improved representation quality and interpretability. Code is available at https://github.com/Jathurshan0330/TFM-Tokenizer.