SOURCE-LINKED INTELLIGENCE

EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limits clinical trust and neuroscientific validation. We propose a unified attribution framework for interpreting EEG foundation models across heterogeneous architectures. The framework integrates gradient-, perturbation-, and activation-based explanation methods to analyze model behavior in spatial, temporal, and frequency dimensions. Spatially, it identifies critical EEG channels and visualizes their distributions using topographic maps. Temporal

Read original source ↗ Open in workspace

recordType

paper

region

Global