3 papers
cs.LG2026
Critical Percolation as a Synthetic Data Model for Interpretability
Aryeh Brill, Tom Ingebretsen Carlson
Neural networks learn features that reflect the hierarchical, multi-scale structure of natural data. Synthetic datasets used to evaluate interpretability methods typically lack thi…
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…
cs.LG2025
Representation Learning on a Random Lattice
Aryeh Brill
Decomposing a deep neural network's learned representations into interpretable features could greatly enhance its safety and reliability. To better understand features, we adopt a…