{"list":"other","total":87,"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"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":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"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":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"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":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2005.00631","title":"Evaluating and Aggregating Feature-based Model Explanations","created":"2020-05-01","cited_by_count":188},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"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":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113},{"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":"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":"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":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87},{"id":"1905.06642","title":"The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA","created":"2019-05-16","cited_by_count":86},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80},{"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":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","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":"1411.3230","title":"Sparse Modeling for Image and Vision Processing","created":"2014-11-12","cited_by_count":48},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48},{"id":"2006.14748","title":"Proper Network Interpretability Helps Adversarial Robustness in Classification","created":"2020-06-26","cited_by_count":41},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39},{"id":"1709.00614","title":"On Identifiability of Nonnegative Matrix Factorization","created":"2017-09-02","cited_by_count":34},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33},{"id":"2410.22366","title":"One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models","created":"2024-10-28","cited_by_count":33},{"id":"1910.07387","title":"Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms","created":"2019-10-16","cited_by_count":32},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32},{"id":"1601.02049","title":"A note on the sample complexity of the Er-SpUD algorithm by Spielman, Wang and Wright for exact recovery of sparsely used dictionaries","created":"2016-01-08","cited_by_count":26},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24},{"id":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23},{"id":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","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":"1705.03239","title":"Convolutional Dictionary Learning via Local Processing","created":"2017-05-09","cited_by_count":19},{"id":"2411.08790","title":"Can sparse autoencoders be used to decompose and interpret steering vectors?","created":"2024-11-13","cited_by_count":19},{"id":"1405.6472","title":"Fast and Robust Archetypal Analysis for Representation Learning","created":"2014-05-26","cited_by_count":15},{"id":"1803.04022","title":"Deep Dictionary Learning: A PARametric NETwork Approach","created":"2018-03-11","cited_by_count":12},{"id":"1312.7604","title":"Probabilistic Archetypal Analysis","created":"2013-12-29","cited_by_count":11},{"id":"1705.02994","title":"Non-negative Matrix Factorization via Archetypal Analysis","created":"2017-05-08","cited_by_count":11},{"id":"2209.11002","title":"Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing","created":"2022-09-22","cited_by_count":11},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11},{"id":"1805.11155","title":"Unsupervised Learning of Artistic Styles with Archetypal Style Analysis","created":"2018-05-28","cited_by_count":10},{"id":"2109.06610","title":"Statistical limits of dictionary learning: random matrix theory and the spectral replica method","created":"2021-09-14","cited_by_count":10},{"id":"1410.7220","title":"Exact and Heuristic Algorithms for Semi-Nonnegative Matrix Factorization","created":"2014-10-27","cited_by_count":9},{"id":"2002.00815","title":"Learning Extremal Representations with Deep Archetypal Analysis","created":"2020-02-03","cited_by_count":9},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9},{"id":"2012.02134","title":"K-Deep Simplex: Deep Manifold Learning via Local Dictionaries","created":"2020-12-03","cited_by_count":8},{"id":"1809.09639","title":"Sparse Recovery and Dictionary Learning from Nonlinear Compressive Measurements","created":"2018-09-25","cited_by_count":4},{"id":"1810.00919","title":"Robust multivariate and functional archetypal analysis with application to financial time series analysis","created":"2018-10-01","cited_by_count":4},{"id":"2101.08083","title":"Developments and applications of Shapley effects to reliability-oriented sensitivity analysis with correlated inputs","created":"2021-01-20","cited_by_count":4},{"id":"2301.10002","title":"Beyond $\\ell_1$ sparse coding in V1","created":"2023-01-24","cited_by_count":4},{"id":"2502.04172","title":"Archetypal Analysis for Binary Data","created":"2025-02-06","cited_by_count":2}],"next_cursor":null}