{"total":90,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56,"area":null},{"id":"2302.10908","title":"Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2304.05538","title":"ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification","created":"2023-04-11","cited_by_count":33,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"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":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2206.05487","title":"Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena","created":"2022-06-11","cited_by_count":21,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2109.11495","title":"DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2102.01792","title":"A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2308.16316","title":"Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2108.12931","title":"NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2109.04374","title":"IFBiD: Inference-Free Bias Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2504.08842","title":"Towards Combinatorial Interpretability of Neural Computation","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2203.09505","title":"Visualizing Global Explanations of Point Cloud DNNs","created":"2022-03-17","cited_by_count":8,"area":null},{"id":"2208.06894","title":"The SVD of Convolutional Weights: A CNN Interpretability Framework","created":"2022-08-14","cited_by_count":8,"area":null},{"id":"2305.08950","title":"Causal Analysis for Robust Interpretability of Neural Networks","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2110.04158","title":"Explainability-Aware One Point Attack for Point Cloud Neural Networks","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2206.10611","title":"Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2103.10229","title":"Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles","created":"2021-03-18","cited_by_count":6,"area":null},{"id":"2107.00296","title":"Explainable Diabetic Retinopathy Detection and Retinal Image Generation","created":"2021-07-01","cited_by_count":6,"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":"2401.06462","title":"AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding","created":"2024-01-12","cited_by_count":6,"area":null},{"id":"2502.13062","title":"AI-Assisted Decision Making with Human Learning","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2307.06913","title":"Uncovering Unique Concept Vectors through Latent Space Decomposition","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2309.07056","title":"Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments","created":"2023-09-13","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":"2411.03993","title":"Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations","created":"2024-11-06","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":"2312.02470","title":"Generator Born from Classifier","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2403.09480","title":"What Sketch Explainability Really Means for Downstream Tasks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2506.00698","title":"Concept-Centric Token Interpretation for Vector-Quantized Generative Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2106.05037","title":"Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2203.16475","title":"Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2211.09859","title":"Data-Centric Debugging: mitigating model failures via targeted data collection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2402.08466","title":"Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2502.16105","title":"NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2101.12447","title":"The Mind's Eye: Visualizing Class-Agnostic Features of CNNs","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2102.04247","title":"Convolutional Neural Network Interpretability with General Pattern Theory","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2105.07054","title":"Face Attributes as Cues for Deep Face Recognition Understanding","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2106.13933","title":"Inverting and Understanding Object Detectors","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2303.09941","title":"Leaping Into Memories: Space-Time Deep Feature Synthesis","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2308.09464","title":"Data augmentation and explainability for bias discovery and mitigation in deep learning","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2410.16958","title":"Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2505.22199","title":"Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2101.06773","title":"Generating Attribution Maps with Disentangled Masked Backpropagation","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2111.04309","title":"Assessing learned features of Deep Learning applied to EEG","created":"2021-11-08","cited_by_count":1,"area":null},{"id":"2203.13453","title":"Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2302.10763","title":"Contrastive Learning and the Emergence of Attributes Associations","created":"2023-02-12","cited_by_count":1,"area":null},{"id":"2309.17144","title":"Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2404.18760","title":"Flow AM: Generating Point Cloud Global Explanations by Latent Alignment","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2408.01139","title":"Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2508.07281","title":"Representation Understanding via Activation Maximization","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2511.08854","title":"Decomposition of Small Transformer Models","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.04548","title":"Identifying Good and Bad Neurons for Task-Level Controllable LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2106.12562","title":"Feature Alignment as a Generative Process","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2107.07005","title":"WeightScale: Interpreting Weight Change in Neural Networks","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2112.15571","title":"PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2211.06843","title":"Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning","created":"2022-11-13","cited_by_count":0,"area":null},{"id":"2306.13178","title":"Targeted Background Removal Creates Interpretable Feature Visualizations","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2308.00858","title":"Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2309.14715","title":"Explaining Deep Face Algorithms through Visualization: A Survey","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2310.07184","title":"NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations","created":"2023-10-11","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":"2409.00069","title":"How to Measure Human-AI Prediction Accuracy in Explainable AI Systems","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2410.14461","title":"The Propensity for Density in Feed-forward Models","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2412.10457","title":"Explaining Model Overfitting in CNNs via GMM Clustering","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2506.04379","title":"Visualizing and Controlling Cortical Responses Using Voxel-Weighted Activation Maximization","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.17040","title":"Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2507.18681","title":"Concept Probing: Where to Find Human-Defined Concepts (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2511.20934","title":"Guaranteed Optimal Compositional Explanations for Neurons","created":"2025-11-25","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}],"next_cursor":null}