Mechanistic Interpretability for Vision at CVPR 2025 (Non-proceedings Track)

Accepted papers (8)

Fetched from OpenReview (v2) on 2026-06-10.

1. ☆$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models

   Dahye Kim, Xavier Thomas, Deepti Ghadiyaram · PDF

2. ☆Explaining Low Perception Model Competency with High-Competency Counterfactuals

   Sara Michelle Pohland, Claire Tomlin · PDF

3. ☆From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport

   Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski · PDF

4. ☆Interpreting large text-to-image diffusion models with dictionary learning

   Stepan Shabalin, Dmitrii Kharlapenko, Ayush Panda, Sheikh Abdur Raheem Ali, Yixiong Hao, Arthur Conmy · PDF

5. ☆Patch Explorer: Interpreting Diffusion Models through Interaction

   Imke Grabe, Jaden Fiotto Kaufman, Rohit Gandikota, David Bau · PDF

6. ☆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 Aaron Richards · PDF

7. ☆Too Late to Recall: The Two-Hop Problem in Multimodal Knowledge Retrieval

   Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda · PDF

8. ☆Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

   Viacheslav Surkov, Chris Wendler, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar Gulcehre · PDF