Victor Boutin

6

Papers

30

Total Citations

Papers (6)

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

NeurIPS 2025arXiv

Saliency strikes back: How filtering out high frequencies improves white-box explanations

Diversity vs. Recognizability: Human-like generalization in one-shot generative models

NeurIPS 2022arXiv

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

NeurIPS 2023arXiv