Interpretability

A Layer-wise Analysis of Supervised Fine-Tuning ACL 2026 Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers CVPR 2026 Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning ACL 2026 Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models CVPR 2026 Can LLM Safety Be Ensured by Constraining Parameter Regions? ACL 2026 Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosis MIDL 2026 EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors MIDL 2026 From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition CVPR 2026 Global Information Thresholding for Sufficient and Necessary Circuits CVPR 2026 Globscope: Toward a Global View of the Loss Landscape CVPR 2026 Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition CVPR 2026 H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers CVPR 2026 Make it SING: Analyzing Semantic Invariants in Classifiers CVPR 2026 Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 Probing Functional Correctness in Diffusion Language Models ACL 2026 SoftCAM: Making black box models self-explainable for medical image analysis MIDL 2026 TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026 Think Less, Code Better: Probing When Chain-of-Thought Hurts and How to Route Around It ACL 2026 Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures ACL 2026 Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures ACL 2026 Tracing Logit Trajectories Across Layer Depth: Dataset-Level Explainability for Language Models ACL 2026 What Fine-Tuning Changes: A Radiomic Lens on Prostate Foundation Model Representations MIDL 2026 When Do Models Actually Decide? Mapping the Layer-Wise Decision Timeline in Pretrained Neural Networks CVPR 2026 Attention IoU: Examining Biases in CelebA using Attention Maps CVPR 2025 BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation AAAI 2025