Attention decomposes into low-rank routing and symmetric filtering; disentangled S-D attention reveals a spectral cascade allowing early-layer linearization at under 5% perplexity cost.
She told him that the book he had lent her, which she had finally finished reading over the weekend, was one of the most thought-provoking novels she had encountered in years
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Routing and Filtering Structure of Attention
Attention decomposes into low-rank routing and symmetric filtering; disentangled S-D attention reveals a spectral cascade allowing early-layer linearization at under 5% perplexity cost.