# Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization

arXiv: https://arxiv.org/abs/2510.20853 · HTML: https://mlsanity.com/paper/2510.20853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling](https://mlsanity.com/paper/2403.03234/) (2024)
- [The Temple University Hospital Seizure Detection Corpus](https://mlsanity.com/paper/1801.08085/) (2018)
- [Neuro-GPT: Towards A Foundation Model for EEG](https://mlsanity.com/paper/2311.03764/) (2023)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification](https://mlsanity.com/paper/2405.19363/) (2024)
- [SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model](https://mlsanity.com/paper/2405.11831/) (2024)
- [BrainWave: A Brain Signal Foundation Model for Clinical Applications](https://mlsanity.com/paper/2402.10251/) (2024)
- [NeurIPT: Foundation Model for Neural Interfaces](https://mlsanity.com/paper/2510.16548/) (2025)
- [Decoding Taste Information in Human Brain: A Temporal and Spatial Reconstruction Data Augmentation Method Coupled with Taste EEG](https://mlsanity.com/paper/2307.05365/) (2023)

## Abstract (arXiv)

Electrophysiological (ExG) signals offer valuable insights into human physiology, yet building foundation models that generalize across everyday tasks remains challenging due to two key limitations: (i)~insufficient data diversity, as most ExG recordings are collected in controlled labs with bulky, expensive devices; and (ii)~task-specific model designs that require tailored processing (i.e., targeted frequency filters) and architectures, which limit generalization across tasks. To address these challenges, we introduce an approach for scalable, task-agnostic ExG monitoring in the wild. We collected 50 hours of unobtrusive free-living ExG data with an earphone-based hardware prototype to narrow the data diversity gap. At the core of our approach is Physiology-informed Multi-band Tokenization (PiMT), which decomposes ExG signals into 12 physiology-informed tokens, followed by a reconstruction task to learn robust representations. This enables adaptive feature recognition across the full frequency spectrum while capturing task-relevant information. Experiments on our new DailySense dataset, the first to enable ExG-based analysis across five human senses, together with four public ExG benchmarks, demonstrate that PiMT consistently outperforms state-of-the-art methods across diverse tasks.