SOURCE-LINKED INTELLIGENCE

Adaptive Anisotropic Attention for Axis-Structured Signals

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Dense self-attention treats all token pairs as equally plausible before learning, an interaction-isotropic prior that can be mismatched to structured signals. For structured, low signal-to-noise ratio (SNR) signals such as EEG, dependencies are organized along the electrode and time axes, and this uniform prior exposes each token to many irrelevant interactions. We introduce Adaptive Anisotropic Attention (AAA), which splits attention into two paths: a temporal path, where each token attends to the tokens of its own electrode across time, and a spatial path, where it attends to the tokens of t

Read original source ↗ Open in workspace

recordType

paper

region

Global