Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

7 February 2022

Papers citing "Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence"

8 / 8 papers shown

Title
Steering CLIP's vision transformer with sparse autoencoders Sonia Joseph Praneet Suresh Ethan Goldfarb Lorenz Hufe Yossi Gandelsman Robert Graham Danilo Bzdok Wojciech Samek Blake A. Richards 24 1 0 11 Apr 2025
Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations Eren Erogullari Sebastian Lapuschkin Wojciech Samek Frederik Pahde LLMSV CoGe 37 1 0 07 Mar 2025
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go? Jae Hee Lee Georgii Mikriukov Gesina Schwalbe Stefan Wermter D. Wolter 16 1 0 20 Sep 2024
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression Dilyara Bareeva Maximilian Dreyer Frederik Pahde Wojciech Samek Sebastian Lapuschkin KELM 22 1 0 15 Apr 2024
Concept Activation Regions: A Generalized Framework For Concept-Based Explanations Jonathan Crabbé M. Schaar 18 30 0 22 Sep 2022
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 88 178 0 21 Sep 2022
Post-hoc Concept Bottleneck Models Mert Yuksekgonul Maggie Wang James Y. Zou 105 114 0 31 May 2022
Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement Leander Weber Sebastian Lapuschkin Alexander Binder Wojciech Samek 8 1 0 15 Mar 2022