Interpretability

CIGMA: Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision Transformers CVPR 2026 From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition CVPR 2026 I'm a Map! Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers CVPR 2026 Intrinsic Concept Extraction Based on Compositional Interpretability CVPR 2026 Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation CVPR 2026 Attention IoU: Examining Biases in CelebA using Attention Maps CVPR 2025 A Unified, Resilient, and Explainable Adversarial Patch Detector CVPR 2025 BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation AAAI 2025 Beyond Position: the emergence of wavelet-like properties in Transformers ACL 2025 Explaining ViTs Using Information Flow AISTATS 2025 From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens EMNLP 2025 Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference CVPR 2025 Interpretable Image Classification via Non-parametric Part Prototype Learning CVPR 2025 LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions CVPR 2025 LLMs Don’t Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations EMNLP 2025 Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis CVPR 2025 ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation AAAI 2025 Spatial Layouts in News Homepages Capture Human Preferences EMNLP 2025 Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition CVPR 2025 Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention AAAI 2024 B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable NeurIPS 2024 CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation CVPR 2024 Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP NeurIPS 2024 Diffusion PID: Interpreting Diffusion via Partial Information Decomposition NeurIPS 2024 Discovering and Mitigating Visual Biases through Keyword Explanation CVPR 2024