{"total":306,"rows":[{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281,"area":null},{"id":"2101.12037","title":"BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data","created":"2021-01-28","cited_by_count":199,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"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":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2111.11745","title":"Intriguing Findings of Frequency Selection for Image Deblurring","created":"2021-11-23","cited_by_count":81,"area":null},{"id":"2401.14461","title":"Marabou 2.0: A Versatile Formal Analyzer of Neural Networks","created":"2024-01-25","cited_by_count":81,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"area":null},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2201.09679","title":"A Review of Deep Transfer Learning and Recent Advancements","created":"2022-01-19","cited_by_count":57,"area":null},{"id":"2107.13509","title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","created":"2021-07-28","cited_by_count":48,"area":null},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2102.03924","title":"Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve","created":"2021-02-07","cited_by_count":46,"area":null},{"id":"2210.04524","title":"Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation","created":"2022-10-10","cited_by_count":45,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2111.14248","title":"Fed2: Feature-Aligned Federated Learning","created":"2021-11-28","cited_by_count":42,"area":null},{"id":"2204.13738","title":"One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation","created":"2022-04-28","cited_by_count":40,"area":null},{"id":"2105.06625","title":"Biometrics: Trust, but Verify","created":"2021-05-14","cited_by_count":39,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2302.14673","title":"Attention-based Point Cloud Edge Sampling","created":"2023-02-28","cited_by_count":37,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2310.18589","title":"This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations","created":"2023-10-28","cited_by_count":36,"area":null},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34,"area":null},{"id":"2207.09679","title":"Explaining Deepfake Detection by Analysing Image Matching","created":"2022-07-20","cited_by_count":34,"area":null},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34,"area":null},{"id":"2302.00799","title":"Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI","created":"2023-02-01","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":"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":"2308.02983","title":"Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection","created":"2023-08-06","cited_by_count":32,"area":null},{"id":"2302.12828","title":"SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries","created":"2023-02-24","cited_by_count":31,"area":null},{"id":"2204.02735","title":"Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck","created":"2022-04-06","cited_by_count":30,"area":null},{"id":"2212.02295","title":"Block Selection Method for Using Feature Norm in Out-of-distribution Detection","created":"2022-12-05","cited_by_count":30,"area":null},{"id":"2212.11737","title":"The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations","created":"2022-12-22","cited_by_count":29,"area":null},{"id":"2302.13080","title":"Does a Neural Network Really Encode Symbolic Concepts?","created":"2023-02-25","cited_by_count":27,"area":null},{"id":"2104.05895","title":"IMAGINE: Image Synthesis by Image-Guided Model Inversion","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"area":null},{"id":"2202.07054","title":"Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2403.17299","title":"Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs","created":"2024-03-26","cited_by_count":24,"area":null},{"id":"2104.11883","title":"Carrying out CNN Channel Pruning in a White Box","created":"2021-04-24","cited_by_count":22,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22,"area":null},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"area":null},{"id":"2103.05086","title":"How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines","created":"2021-03-08","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2109.09150","title":"A Study of the Generalizability of Self-Supervised Representations","created":"2021-09-19","cited_by_count":18,"area":null},{"id":"2110.10136","title":"Activation Landscapes as a Topological Summary of Neural Network Performance","created":"2021-10-19","cited_by_count":18,"area":null},{"id":"2401.08527","title":"MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment","created":"2024-01-16","cited_by_count":18,"area":null},{"id":"2106.10606","title":"Attack to Fool and Explain Deep Networks","created":"2021-06-20","cited_by_count":17,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17,"area":null},{"id":"2106.10938","title":"A Game-Theoretic Taxonomy of Visual Concepts in DNNs","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2104.03414","title":"PrivateSNN: Privacy-Preserving Spiking Neural Networks","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","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":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2401.16318","title":"Defining and Extracting generalizable interaction primitives from DNNs","created":"2024-01-29","cited_by_count":14,"area":null},{"id":"2203.16530","title":"Learning Instance-Specific Adaptation for Cross-Domain Segmentation","created":"2022-03-30","cited_by_count":13,"area":null},{"id":"2308.04761","title":"Feature Matching Data Synthesis for Non-IID Federated Learning","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2308.11098","title":"On the Interpretability of Quantum Neural Networks","created":"2023-08-22","cited_by_count":13,"area":null},{"id":"2407.19198","title":"Towards the Dynamics of a DNN Learning Symbolic Interactions","created":"2024-07-27","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":"2111.03549","title":"Interpreting Representation Quality of DNNs for 3D Point Cloud Processing","created":"2021-11-05","cited_by_count":12,"area":null},{"id":"2111.12886","title":"Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN","created":"2021-11-25","cited_by_count":12,"area":null},{"id":"2203.14932","title":"Attributable Visual Similarity Learning","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2206.09868","title":"Understanding Robust Learning through the Lens of Representation Similarities","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2210.16114","title":"Towards Reliable Neural Specifications","created":"2022-10-28","cited_by_count":12,"area":null},{"id":"2304.13312","title":"Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs","created":"2023-04-26","cited_by_count":12,"area":null},{"id":"2305.00537","title":"Interpretability of Machine Learning: Recent Advances and Future Prospects","created":"2023-04-30","cited_by_count":12,"area":null},{"id":"2311.08968","title":"Identifying Linear Relational Concepts in Large Language Models","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2408.12804","title":"Universal dimensions of visual representation","created":"2024-08-23","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":"2302.04032","title":"A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions","created":"2023-02-08","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":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2110.07305","title":"DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2205.08399","title":"How do Variational Autoencoders Learn? Insights from Representational Similarity","created":"2022-05-17","cited_by_count":10,"area":null},{"id":"2307.10792","title":"Optimizing PatchCore for Few/many-shot Anomaly Detection","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2308.11223","title":"LDP-Feat: Image Features with Local Differential Privacy","created":"2023-08-22","cited_by_count":10,"area":null},{"id":"2507.10846","title":"Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2102.11011","title":"The Uncanny Similarity of Recurrence and Depth","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2109.00951","title":"GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps","created":"2021-09-02","cited_by_count":9,"area":null},{"id":"2110.15288","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2112.14015","title":"GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference","created":"2021-12-28","cited_by_count":9,"area":null},{"id":"2208.06612","title":"Interpreting BERT-based Text Similarity via Activation and Saliency Maps","created":"2022-08-13","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":"2203.09505","title":"Visualizing Global Explanations of Point Cloud DNNs","created":"2022-03-17","cited_by_count":8,"area":null},{"id":"2206.08500","title":"What do navigation agents learn about their environment?","created":"2022-06-17","cited_by_count":8,"area":null},{"id":"2210.06924","title":"Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks","created":"2022-10-13","cited_by_count":8,"area":null}],"next_cursor":"100"}