{"total":65,"rows":[{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33,"area":null},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2205.12423","title":"Deletion and Insertion Tests in Regression Models","created":"2022-05-25","cited_by_count":14,"area":null},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2301.11722","title":"Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?","created":"2023-01-27","cited_by_count":10,"area":"diffusion"},{"id":"2504.16940","title":"Better artificial intelligence does not mean better models of biology","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2311.14435","title":"Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2312.06627","title":"An adversarial attack approach for eXplainable AI evaluation on deepfake detection models","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2404.18649","title":"Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection","created":"2024-04-29","cited_by_count":6,"area":null},{"id":"2305.14979","title":"Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2505.13118","title":"Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2601.05328","title":"Bi-Orthogonal Factor Decomposition for Vision Transformers","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2209.11539","title":"Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models","created":"2022-09-23","cited_by_count":4,"area":null},{"id":"2305.02679","title":"Neighboring Words Affect Human Interpretation of Saliency Explanations","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2408.07828","title":"Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systems","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2506.05774","title":"Evaluating Neuron Explanations: A Unified Framework with Sanity Checks","created":"2025-06-06","cited_by_count":4,"area":"mechinterp"},{"id":"2210.04491","title":"A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2307.09591","title":"Saliency strikes back: How filtering out high frequencies improves white-box explanations","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2310.01828","title":"Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentation","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2511.10439","title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2309.12214","title":"Can We Reliably Improve the Robustness to Image Acquisition of Remote Sensing of PV Systems?","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2409.17370","title":"The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2502.03957","title":"Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2503.03283","title":"Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2605.19607","title":"Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2410.08069","title":"Unlearning-based Neural Interpretations","created":"2024-10-10","cited_by_count":1,"area":"safety"},{"id":"2410.24050","title":"A Mechanistic Study of Transformers Training Dynamics","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2512.11433","title":"Back to the Baseline: Examining Baseline Effects on Explainability Metrics","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2606.00082","title":"Hoeffding Concept Bottleneck Models with Applications to Overhead Images","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.18008","title":"PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution","created":"2026-06-16","cited_by_count":1,"area":"mllm"},{"id":"2307.08880","title":"Modular Neural Network Approaches for Surgical Image Recognition","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2406.05598","title":"Understanding Inhibition Through Maximally Tense Images","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2503.03443","title":"Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2505.00220","title":"Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.09660","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2506.18751","title":"Sensitivity analysis of image classification models using generalized polynomial chaos","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2506.19630","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2601.00355","title":"The Impact of Lesion Focus on the Performance of AI-Based Melanoma Classification","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2603.15867","title":"Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2607.27904","title":"Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.11064","title":"Entropy-Centric Explainable AI for Remote Sensing Image Segmentation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}