{"total":68,"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":"2104.13369","title":"Explaining in Style: Training a GAN to explain a classifier in StyleSpace","created":"2021-04-27","cited_by_count":122,"area":null},{"id":"2204.00008","title":"Improving Adversarial Transferability via Neuron Attribution-Based Attacks","created":"2022-03-31","cited_by_count":93,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64,"area":null},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55,"area":null},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33,"area":null},{"id":"2108.01070","title":"Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution","created":"2021-08-02","cited_by_count":26,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2210.14226","title":"FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks","created":"2022-10-25","cited_by_count":23,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2409.19403","title":"Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration","created":"2024-09-28","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2102.06761","title":"MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset","created":"2021-02-12","cited_by_count":15,"area":null},{"id":"2110.03485","title":"Cartoon Explanations of Image Classifiers","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2208.00781","title":"Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods","created":"2022-07-26","cited_by_count":15,"area":null},{"id":"2101.10552","title":"A Unified Paths Perspective for Pruning at Initialization","created":"2021-01-26","cited_by_count":14,"area":null},{"id":"2206.00700","title":"RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2503.09046","title":"Discovering Influential Neuron Path in Vision Transformers","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2201.09205","title":"Deeply Explain CNN via Hierarchical Decomposition","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2209.04138","title":"Adapting to Non-Centered Languages for Zero-shot Multilingual Translation","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2305.01361","title":"Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature","created":"2023-05-02","cited_by_count":6,"area":null},{"id":"2406.16955","title":"SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2205.10900","title":"Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization","created":"2022-05-22","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2305.17409","title":"On the special role of class-selective neurons in early training","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2306.13753","title":"Four Axiomatic Characterizations of the Integrated Gradients Attribution Method","created":"2023-06-23","cited_by_count":5,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2110.08429","title":"TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models","created":"2021-10-16","cited_by_count":4,"area":null},{"id":"2111.15414","title":"Neuron with Steady Response Leads to Better Generalization","created":"2021-11-30","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":"2502.14671","title":"Explanations of Large Language Models Explain Language Representations in the Brain","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2201.01164","title":"Interpretable Low-Resource Legal Decision Making","created":"2022-01-01","cited_by_count":3,"area":null},{"id":"2106.15835","title":"Robust and Interpretable Temporal Convolution Network for Event Detection in Lung Sound Recordings","created":"2021-06-30","cited_by_count":2,"area":null},{"id":"2508.20353","title":"DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2604.13258","title":"Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2606.00557","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2102.11010","title":"Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2203.02592","title":"Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2211.10796","title":"Quantifying Human Bias and Knowledge to guide ML models during Training","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2303.08035","title":"ISimDL: Importance Sampling-Driven Acceleration of Fault Injection Simulations for Evaluating the Robustness of Deep Learning","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2408.14681","title":"Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2509.12039","title":"RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2601.04098","title":"Layer-wise Positional Bias in Short-Context Language Modeling","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2106.05825","title":"HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2112.06219","title":"Visualising and Explaining Deep Learning Models for Speech Quality Prediction","created":"2021-12-12","cited_by_count":0,"area":null},{"id":"2202.01096","title":"Identifying Suitable Tasks for Inductive Transfer Through the Analysis of Feature Attributions","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2309.16916","title":"ONNXExplainer: an ONNX Based Generic Framework to Explain Neural Networks Using Shapley Values","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2405.19886","title":"Federated Learning with Multi-resolution Model Broadcast","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2409.09088","title":"Y-Drop: A Conductance based Dropout for fully connected layers","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2409.16865","title":"Linking in Style: Understanding learned features in deep learning models","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2503.12683","title":"Algebraic Adversarial Attacks on Explainability Models","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2503.16583","title":"Explainable AI-Guided Efficient Approximate DNN Generation for Multi-Pod Systolic Arrays","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2507.00037","title":"Model Fusion via Retrofitting","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2510.18636","title":"C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2605.06834","title":"Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.00073","title":"Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.29693","title":"IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.14271","title":"Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist","created":"2026-07-15","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}