3 papers
cs.LG2026
Feature Identification via the Empirical NTK
Jennifer Lin
We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface feature directions in trained neural networks. Across three increasingly realistic…
cond-mat.str-el2026
Instabilities of the Fractionalized Dirac Semimetal in the Kitaev-Kondo Model
Jennifer Lin, Frank Krüger
We study a honeycomb Kondo lattice model in which Dirac conduction electrons are coupled to a spin-1/2 Kitaev quantum spin liquid. For weak Kondo coupling, the spins fractionalize…
hep-th2026
Towards Worst-Case Guarantees with Scale-Aware Interpretability
Lauren Greenspan, David Berman, Aryeh Brill +9
Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, exp…