AI RESEARCH
Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention
arXiv CS.CL
•
ArXi:2605.21842v1 Announce Type: cross Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the energetically dominant, spatially organized patterns that persist amid background chaos -- carry a disproportionate fraction of total energy and govern all transport. We propose that tokens play an analogous role in transformer attention: informationally dense positions (morphological boundaries, syntactic heads, dis.