---
format: "aidr-story-markdown/v1"
id: "c5e0cf186093ad288b34deb76d7f029c050f34a5633a8ac938ab3cc032df6fb5"
canonical_url: "https://aidr.today/c5e0cf18?lang=en"
title: "SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-09T04:00:00.000Z"
category: "Research"
topics: []
source_urls: ["https://arxiv.org/abs/2610.10571"]
summary: "SPERA is an EEG foundation model that uses a joint-embedding predictive architecture to predict in latent space. It incorporates a Legendre-polynomial spatial prior to encode varying scalp electrode geometries."
---

# SPERA: Spherical Prior EEG Foundation Model with Geometry\- and Frequency\-Aware Latent Prediction

> [Open the canonical story](<https://aidr.today/c5e0cf18?lang=en>)

**Published:** 2026-10-09T04:00:00.000Z
**Category:** Research

## Summary

SPERA is an EEG foundation model that uses a joint\-embedding predictive architecture to predict in latent space\. It incorporates a Legendre\-polynomial spatial prior to encode varying scalp electrode geometries\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.10571>)