Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models

10 February 2025

Papers citing "Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models"

2 / 2 papers shown

Title
Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive Analysis Frank Li Hari M. Trivedi Bardia Khosravi Theo Dapamede Mohammadreza Chavoshi ... Rohan Isaac Aawez Mansuri Janice Newsome S. Purkayastha J. Gichoya LM&MA 29 0 0 22 Apr 2025
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models Mateusz Pach Shyamgopal Karthik Quentin Bouniot Serge Belongie Zeynep Akata VLM 62 0 0 03 Apr 2025