KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation

2026-05-13

AI Summary

Existing foundational EEG models struggle to effectively capture non-Euclidean spatiotemporal topologies and face a significant modality gap between physiological signals and textual semantics. To address these limitations, this work proposes KAST-BAR, the first model to integrate expert medical knowledge into EEG representation learning. It employs a Dual-Stream Hierarchical Attention (DSHA) encoder to model complex brain network structures, a Knowledge-Anchored Semantic Parser (KASP) to generate instance-level textual profiles, and a Semantic Text-Aware Refiner (STAR) to dynamically reconstruct EEG representations, thereby aligning neural signals with high-level semantic space. Pretrained on 21 datasets, KAST-BAR achieves state-of-the-art performance across six downstream tasks, substantially advancing generalizable neural decoding capabilities.

Abstract

While EEG foundation models have shown significant potential in universal neural decoding across tasks, their advancement remains constrained by the inadequacy modeling of complex spatiotemporal topology, as well as the inherent modality gap between low-level physiological signals and high-level textual semantics. To address these challenges, we propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR), which dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space. Specifically, we design a Dual-Stream Hierarchical Attention (DSHA) encoder that accurately captures the brain's intrinsic non-Euclidean topology by modeling local temporal dynamics with global spatial contexts. On this basis, a Knowledge-Anchored Semantic Profiler (KASP) is proposed to synthesize physically-grounded and instance-level textual profiles, which subsequently drive a Semantic Text-Aware Refiner (STAR) to dynamically reconstruct EEG representations using Latent Expert Queries. By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks. Our code is available at https://github.com/KAST-BAR/KAST-BAR

Problem

• EEG foundation models
• spatiotemporal topology
• modality gap
• neural decoding
• physiological signals

Innovation

• Knowledge-Anchored
• Semantically-Dynamic Topology
• Dual-Stream Hierarchical Attention
• Latent Expert Queries
• EEG Foundation Model