{"total":103,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"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":"2210.07506","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","created":"2022-10-14","cited_by_count":86,"area":null},{"id":"2105.05330","title":"Neuro-Symbolic Artificial Intelligence: Current Trends","created":"2021-05-11","cited_by_count":54,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50,"area":null},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2303.13995","title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","created":"2023-03-24","cited_by_count":34,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2310.07473","title":"FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation","created":"2023-10-11","cited_by_count":22,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2105.04854","title":"Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity","created":"2021-05-11","cited_by_count":20,"area":null},{"id":"2204.01208","title":"Attribute Prototype Network for Any-Shot Learning","created":"2022-04-04","cited_by_count":19,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2311.04157","title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","created":"2023-11-07","cited_by_count":15,"area":null},{"id":"2511.22697","title":"Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations","created":"2025-11-27","cited_by_count":15,"area":"mllm"},{"id":"2305.15134","title":"Networks are Slacking Off: Understanding Generalization Problem in Image Deraining","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2103.05997","title":"Quality-Aware Network for Human Parsing","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11,"area":null},{"id":"2209.07225","title":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2211.02912","title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2310.15368","title":"Deep Integrated Explanations","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2212.09206","title":"Segmentation Ability Map: Interpret deep features for medical image segmentation","created":"2022-12-19","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":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2410.06352","title":"Tree-Based Leakage Inspection and Control in Concept Bottleneck Models","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2502.10556","title":"Recent Advances in Malware Detection: Graph Learning and Explainability","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2103.09716","title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2108.01335","title":"Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability","created":"2021-08-03","cited_by_count":6,"area":null},{"id":"2112.03020","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2202.09374","title":"Explaining, Evaluating and Enhancing Neural Networks' Learned Representations","created":"2022-02-18","cited_by_count":6,"area":null},{"id":"2205.02698","title":"Do Different Deep Metric Learning Losses Lead to Similar Learned Features?","created":"2022-05-05","cited_by_count":6,"area":null},{"id":"2404.13567","title":"On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2106.13734","title":"Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis","created":"2021-06-25","cited_by_count":5,"area":null},{"id":"2303.10523","title":"Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2307.04343","title":"Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2103.10773","title":"UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning","created":"2021-03-19","cited_by_count":4,"area":null},{"id":"2108.10360","title":"Interpreting Face Inference Models using Hierarchical Network Dissection","created":"2021-08-23","cited_by_count":4,"area":null},{"id":"2203.00192","title":"Layer Adaptive Deep Neural Networks for Out-of-distribution Detection","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2203.15704","title":"Fine-Grained Visual Entailment","created":"2022-03-29","cited_by_count":4,"area":"lr"},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2212.01562","title":"Understanding the Robustness of Multi-Exit Models under Common Corruptions","created":"2022-12-03","cited_by_count":4,"area":"inference"},{"id":"2305.01808","title":"Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detection","created":"2023-05-02","cited_by_count":4,"area":null},{"id":"2308.12696","title":"Disentanglement Learning via Topology","created":"2023-08-24","cited_by_count":4,"area":null},{"id":"2502.12600","title":"Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2506.17052","title":"From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2201.12347","title":"Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons","created":"2022-01-31","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":"2206.08661","title":"Boosting Factorization Machines via Saliency-Guided Mixup","created":"2022-06-17","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":"2309.10209","title":"Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2406.09166","title":"Fine-Grained Domain Generalization with Feature Structuralization","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2104.02234","title":"DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2106.04935","title":"Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2106.11054","title":"Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations","created":"2021-06-21","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":"2109.10078","title":"Learning Interpretable Concept Groups in CNNs","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2207.02179","title":"Activation Template Matching Loss for Explainable Face Recognition","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2301.09611","title":"Explaining Deep Learning Hidden Neuron Activations using Concept Induction","created":"2023-01-23","cited_by_count":2,"area":null},{"id":"2307.07620","title":"Generalizable Embeddings with Cross-batch Metric Learning","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2308.03999","title":"Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning","created":"2023-08-08","cited_by_count":2,"area":"lr"},{"id":"2404.14996","title":"CA-Stream: Attention-based pooling for interpretable image recognition","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2205.11109","title":"Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2207.07781","title":"Subgroup Discovery in Unstructured Data","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2210.00992","title":"Feature Embedding by Template Matching as a ResNet Block","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2302.01642","title":"Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image Classification","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2308.09228","title":"Generalized Sum Pooling for Metric Learning","created":"2023-08-18","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":"2404.09768","title":"Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2405.05755","title":"CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2405.09580","title":"Error-margin Analysis for Hidden Neuron Activation Labels","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2406.16975","title":"A Review of Global Sensitivity Analysis Methods and a comparative case study on Digit Classification","created":"2024-06-23","cited_by_count":1,"area":null},{"id":"2409.07024","title":"SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2102.05874","title":"Explainability in CNN Models By Means of Z-Scores","created":"2021-02-11","cited_by_count":0,"area":null},{"id":"2103.11888","title":"Weakly Supervised Recovery of Semantic Attributes","created":"2021-03-22","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":"2212.06299","title":"Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2304.04354","title":"ViT-Calibrator: Decision Stream Calibration for Vision Transformer","created":"2023-04-10","cited_by_count":0,"area":null},{"id":"2305.03919","title":"DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2305.10121","title":"FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2309.02843","title":"Knowledge Distillation Layer that Lets the Student Decide","created":"2023-09-06","cited_by_count":0,"area":"distill"},{"id":"2309.14715","title":"Explaining Deep Face Algorithms through Visualization: A Survey","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2405.13860","title":"MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2406.00555","title":"Length-scale study in deep learning prediction for non-small cell lung cancer brain metastasis","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2410.00524","title":"Deep Model Interpretation with Limited Data : A Coreset-based Approach","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2501.02010","title":"Explainable Neural Networks with Guarantees: A Sparse Estimation Approach","created":"2025-01-02","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}],"next_cursor":"100"}