{"total":990,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"id":"2102.05152","title":"On Explainability of Graph Neural Networks via Subgraph Explorations","created":"2021-02-09","cited_by_count":281,"area":null},{"id":"2302.09880","title":"Towards Unbounded Machine Unlearning","created":"2023-02-20","cited_by_count":268,"area":"safety"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217,"area":"safety"},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143,"area":"distill"},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2303.11570","title":"Boundary Unlearning","created":"2023-03-21","cited_by_count":134,"area":"safety"},{"id":"2201.05629","title":"Zero-Shot Machine Unlearning","created":"2022-01-14","cited_by_count":133,"area":"safety"},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2106.14501","title":"R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network","created":"2021-06-28","cited_by_count":106,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"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":"2203.03373","title":"Adversarial Texture for Fooling Person Detectors in the Physical World","created":"2022-03-07","cited_by_count":96,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2103.05154","title":"Explanations in Autonomous Driving: A Survey","created":"2021-03-09","cited_by_count":81,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2102.01998","title":"Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond","created":"2021-02-03","cited_by_count":76,"area":null},{"id":"2206.02909","title":"Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data","created":"2022-06-06","cited_by_count":75,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"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":"2101.10043","title":"Deep One-Class Classification via Interpolated Gaussian Descriptor","created":"2021-01-25","cited_by_count":67,"area":null},{"id":"2105.13137","title":"Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future","created":"2021-05-27","cited_by_count":67,"area":null},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65,"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":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2101.09864","title":"Applications of Deep Learning in Fundus Images: A Review","created":"2021-01-25","cited_by_count":59,"area":null},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","cited_by_count":59,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2103.10226","title":"Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations","created":"2021-03-18","cited_by_count":56,"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":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54,"area":null},{"id":"2402.10086","title":"Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"id":"2111.00980","title":"Mixture Proportion Estimation and PU Learning: A Modern Approach","created":"2021-11-01","cited_by_count":52,"area":null},{"id":"2507.16991","title":"PyG 2.0: Scalable Learning on Real World Graphs","created":"2025-07-22","cited_by_count":52,"area":null},{"id":"2101.06116","title":"Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects","created":"2021-01-15","cited_by_count":49,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"area":null},{"id":"2306.09346","title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","created":"2023-06-15","cited_by_count":46,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2210.01986","title":"MAtt: A Manifold Attention Network for EEG Decoding","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2112.12089","title":"Reflash Dropout in Image Super-Resolution","created":"2021-12-22","cited_by_count":41,"area":null},{"id":"2401.16765","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","created":"2024-01-30","cited_by_count":41,"area":"safety"},{"id":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39,"area":null},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39,"area":null},{"id":"2210.06959","title":"A Survey on Explainable Anomaly Detection","created":"2022-10-13","cited_by_count":39,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"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":"2312.04095","title":"Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection","created":"2023-12-07","cited_by_count":37,"area":"safety"},{"id":"2103.13859","title":"Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks","created":"2021-03-25","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2202.10553","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","created":"2022-02-16","cited_by_count":35,"area":null},{"id":"2210.15304","title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","created":"2022-10-27","cited_by_count":35,"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":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2102.02811","title":"CrossNorm and SelfNorm for Generalization under Distribution Shifts","created":"2021-02-04","cited_by_count":33,"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":"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":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2103.16886","title":"Neural Response Interpretation through the Lens of Critical Pathways","created":"2021-03-31","cited_by_count":32,"area":null},{"id":"2104.14995","title":"Interpretable Semantic Photo Geolocation","created":"2021-04-30","cited_by_count":32,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"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":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2408.00920","title":"Towards Certified Unlearning for Deep Neural Networks","created":"2024-08-01","cited_by_count":31,"area":"safety"},{"id":"2104.11914","title":"EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case","created":"2021-04-24","cited_by_count":30,"area":null},{"id":"2207.08224","title":"Learning with Recoverable Forgetting","created":"2022-07-17","cited_by_count":30,"area":null},{"id":"2308.02062","title":"Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images","created":"2023-08-03","cited_by_count":30,"area":"diffusion"},{"id":"2107.08264","title":"M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis","created":"2021-07-17","cited_by_count":29,"area":null},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28,"area":null},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28,"area":null}],"next_cursor":"100"}