Accepted Papers

A Case Study on Hidden Bias in Vision-Language Model Activations (Oral)

Arnau Marin-Llobet

Feature Alignment for Scalable B-cosification of Foundational Vision Transformers (Oral)

Raphael Maser, Siddhartha Gairola, Sukrut Rao, Bernt Schiele

FaCT: Faithful Concept Traces for Explaining Neural Networks (Oral)

Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele

LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories (Oral)

Ido Beigelman, Moti Freiman

When Geometry Reverses Topological Conclusions: Evaluating Persistent Homology in Sparse Autoencoders (Oral)

Teresa Zhang

MIMIC: Multimodal Inversion for Model Interpretation and Conceptualization

Animesh Jain, Alexandros Stergiou

Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis

Kyeongryeol Go

Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification

Nghia Nguyen, Tianjiao Ding, Rene Vidal

Gaze Heads: What They See Is What VLMs Say

Rohit Gandikota, David Bau

Learning Sparse Visual Representations via Spatial-Semantic Factorization

Theodore Zhengde Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel C Codella, Tristan Naumann, Hoifung Poon, Mu Wei

Attributes are all you need to quantify Video Complexity

Aditya Sarkar, Yi Li, Jiacheng Cheng, Zihao Wang, Sai Vidyaranya Nuthalapati, Aashu Singh, Shlok Kumar Mishra, David Jacobs, Nuno Vasconcelos

Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning

Nhi Pham, Artur Jesslen, Bernt Schiele, Adam Kortylewski, Jonas Fischer

Simple Localized Counterfactuals for Visual Explanation

David Carlyn, Jianyang Gu, Wei-Lun Chao

Zero-ablation overstates register function in DINO vision transformers

Felipe Parodi, Jordan Kyle Matelsky, Melanie Segado

Faithful Attribution in Vision Transformers via Feature-Gradient Gating

Julius Šula, Thomas Lukasiewicz, Bayar Menzat

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders

Akshay R. Kulkarni, Tsui-Wei Weng, Vivek Narayanaswamy, Shusen Liu, Wesam A. Sakla, Kowshik Thopalli

Concept Spaces in the Residual Stream of Diffusion Transformers

Riyasat Ohib, Meera Hahn, Mani Malek

Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion

Abu Noman Md Sakib, OFM Riaz Rahman Aranya, Kevin Desai, Zijie Zhang

I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers

Alexa R. Tartaglini, Michael A. Lepori

Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representations

David Chapman, Parniyan Farvardin

CAM: Classifier Activation Matching for Minimal Explanation Generation and Sparse Circuit Discovery

Pirzada Suhail, Aditya Anand, Amit Sethi

Differences in Detection: Explainability Where it Matters

Johannes Theodoridis, Johannes Maucher, Andreas Schilling

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

Hannah Gao, Isha Agarwal, Dylan Hadfield-Menell, Rachel Ma