# Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction

arXiv: https://arxiv.org/abs/2603.16281 · HTML: https://mlsanity.com/paper/2603.16281/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 94 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [Deep learning-based electroencephalography analysis: a systematic review](https://mlsanity.com/paper/1901.05498/) (2019)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [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)
- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [Learning by Reconstruction Produces Uninformative Features For Perception](https://mlsanity.com/paper/2402.11337/) (2024)
- [Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning](https://mlsanity.com/paper/2505.12477/) (2025)
- [EEG Foundation Models: A Critical Review of Current Progress and Future Directions](https://mlsanity.com/paper/2507.11783/) (2025)
- [How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks](https://mlsanity.com/paper/2407.03475/) (2024)
- [The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark](https://mlsanity.com/paper/2404.15319/) (2024)
- [EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models](https://mlsanity.com/paper/2508.17742/) (2025)
- [Next-Embedding Prediction Makes Strong Vision Learners](https://mlsanity.com/paper/2512.16922/) (2025)
- [S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention](https://mlsanity.com/paper/2403.11772/) (2024)
- [From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Saptiotemporal Dynamics in Brain Signal Analysis](https://mlsanity.com/paper/2507.03633/) (2025)

## Built on by (most cited first, 4 of 4)

- [Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity](https://mlsanity.com/paper/2604.18058/) (2026)
- [Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning](https://mlsanity.com/paper/2608.21147/) (2026)
- [Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models](https://mlsanity.com/paper/2609.31167/) (2026)
- [SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction](https://mlsanity.com/paper/2610.10571/) (2026)

## Abstract (arXiv)

Electroencephalography (EEG) is a widely used tool for studying brain function, with applications in clinical neuroscience, diagnosis, and brain-computer interfaces (BCIs). Recent EEG foundation models trained on large unlabeled corpora aim to learn transferable representations, but their effectiveness remains unclear; reported improvements over smaller task-specific models are often modest, sensitive to downstream adaptation and fine-tuning strategies, and limited under linear probing. We hypothesize that one contributing factor is the reliance on signal reconstruction as the primary self-supervised learning (SSL) objective, which biases representations toward high-variance artifacts rather than task-relevant neural structure. To address this limitation, we explore an SSL paradigm based on Joint Embedding Predictive Architectures (JEPA), which learn by predicting latent representations instead of reconstructing raw signals. We introduce Laya, the first EEG foundation model based on LeJEPA. We show that latent prediction yields representations that encode semantic structure in EEG: Laya embeddings track clinically meaningful state changes such as seizure onset, are resilient to noise, and achieve the strongest mean clinical accuracy under frozen linear probing, with particular gains on tasks where relevant neural patterns are subtle and easily obscured by artifacts. Controlled ablations against matched MAE variants confirm that the choice of pretraining objective, rather than architecture or data, is the primary driver of these gains.