Skip to content
Research

Adaptive Anisotropic Attention for Axis-Structured Signals.

arXiv:2609.08788v3 Announce Type: replace-cross Abstract: 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 (

arXiv cs.AIResearch source·