A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
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. Under this framework, statistical biases are identified within previous MI paradigms, which reveal that they may either be perceptually uninterpretable to humans (i.e., deviate from the natural image distribution), or mechanistically unfaithful to the vision models (i.e., unable to activate model features). To resolve the biases under the distributional view, we propose a model with a KL-minimal soft-constraint principle for visual MI that theoretically balances interpretability and faithfulness. We realize this principle via energy-guided diffusion posterior sampling. Extensive experiments validate the theoretical soundness of the proposed distributional view and demonstrate the practical effectiveness of our paradigm on the DINOv3 vision model.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the comp…
Multimodal ReasoningVisual ReasoningInterpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Mechanistic interpretability aims to understand the internal mechanisms learned by neural networks. Despite recent progress toward this goal, it remains unclear how best to decompose neural network parameters into mechan…
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understand…
PhilosophySteering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift. In this work, we use mechanistic interpretability to study how robustness-relevant perturbations a…
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
Mechanistic interpretability research faces a gap between analyzing simple circuits in toy tasks and discovering features in large models. To bridge this gap, we propose text-to-SQL generation as an ideal task to study, …
Intent RecognitionText to SQLText-To-SQL