1 citations · 1 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cond-mat.dis-nn2026
Transient Reserves, Sink Dampers, and the Failure of Eigenvalue Reasoning in the Attention Propagator
Li Hengyu
The attention matrix of a causal transformer is row-stochastic, iterated over depth, and non-normal by construction. For non-normal operators, eigenvalues control only asymptotic b…
cs.LG2026
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
Li Hengyu
The pre-softmax score of an attention head is a bilinear form in a learned operator . Because M is generally non-symmetric, hence non-norm…