{"list":"other","total":84,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1910.07738","title":"A Survey of Deep Learning Techniques for Autonomous Driving","created":"2019-10-17","cited_by_count":403},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2403.17806","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","created":"2024-03-26","cited_by_count":149},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"2006.15417","title":"Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors","created":"2020-06-27","cited_by_count":120},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2105.04289","title":"Do Concept Bottleneck Models Learn as Intended?","created":"2021-05-10","cited_by_count":116},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"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},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98},{"id":"2501.16615","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","created":"2025-01-28","cited_by_count":93},{"id":"1912.09818","title":"When Explanations Lie: Why Many Modified BP Attributions Fail","created":"2019-12-20","cited_by_count":92},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88},{"id":"2212.07430","title":"Interactive Concept Bottleneck Models","created":"2022-12-14","cited_by_count":79},{"id":"2110.09485","title":"Learning in High Dimension Always Amounts to Extrapolation","created":"2021-10-18","cited_by_count":66},{"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},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"2104.07059","title":"Neural population geometry: An approach for understanding biological and artificial neural networks","created":"2021-04-14","cited_by_count":52},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39},{"id":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32},{"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},{"id":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23},{"id":"2404.02233","title":"Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models","created":"2024-04-02","cited_by_count":22},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21},{"id":"2408.02265","title":"Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts","created":"2024-08-05","cited_by_count":20},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16},{"id":"2504.19774","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","created":"2025-04-28","cited_by_count":15},{"id":"2312.00110","title":"CLIP-QDA: An Explainable Concept Bottleneck Model","created":"2023-11-30","cited_by_count":13},{"id":"2310.14805","title":"Cross-Modal Conceptualization in Bottleneck Models","created":"2023-10-23","cited_by_count":12},{"id":"1805.11155","title":"Unsupervised Learning of Artistic Styles with Archetypal Style Analysis","created":"2018-05-28","cited_by_count":10},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9},{"id":"2206.10129","title":"Automatic Concept Extraction for Concept Bottleneck-based Video Classification","created":"2022-06-21","cited_by_count":8},{"id":"2310.04929","title":"DISCOVER: Making Vision Networks Interpretable via Competition and Dissection","created":"2023-10-07","cited_by_count":8},{"id":"2502.01048","title":"Sparks of Explainability: Recent Advancements in Explaining Large Vision Models","created":"2025-02-03","cited_by_count":4},{"id":"2507.05810","title":"Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs","created":"2025-07-08","cited_by_count":1}],"next_cursor":null}