AI RESEARCH
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
arXiv CS.CV
•
ArXi:2605.17504v1 Announce Type: new Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top-$K$ activation retrieval or optimization with regularization). In this work, we establish a theoretical distributional view for visual MI, which models the influence of a feature activation on the natural image distribution, thereby formulating a Kullback-Leibler (KL)-minimal optimization problem to model the MI task.