{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"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":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95},{"id":"2501.16615","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","created":"2025-01-28","cited_by_count":93},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71},{"id":"2412.05276","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","created":"2024-12-06","cited_by_count":68},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62},{"id":"1805.07039","title":"A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations","created":"2018-05-18","cited_by_count":60},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47},{"id":"1902.04893","title":"Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps","created":"2019-02-13","cited_by_count":34},{"id":"2312.00869","title":"Segment and Caption Anything","created":"2023-12-01","cited_by_count":30},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25},{"id":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","cited_by_count":23},{"id":"2206.10610","title":"Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability","created":"2022-06-20","cited_by_count":21},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15},{"id":"2307.14239","title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","created":"2023-07-26","cited_by_count":10},{"id":"2508.11277","title":"Probing the Representational Power of Sparse Autoencoders in Vision Models","created":"2025-08-15","cited_by_count":10},{"id":"2107.02033","title":"Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated","created":"2021-07-01","cited_by_count":7},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5},{"id":"2409.14590","title":"Explainable AI needs formalization","created":"2024-09-22","cited_by_count":5},{"id":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5},{"id":"2602.24176","title":"Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions","created":"2026-02-27","cited_by_count":4},{"id":"2306.15111","title":"Self-Supervised Image Captioning with CLIP","created":"2023-06-26","cited_by_count":3},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2}],"next_cursor":null}