{"list":"other","total":73,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2002.03754","title":"Unsupervised Discovery of Interpretable Directions in the GAN Latent Space","created":"2020-02-10","cited_by_count":289},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"1810.10531","title":"A mathematical theory of semantic development in deep neural networks","created":"2018-10-23","cited_by_count":186},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"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":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"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":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124},{"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":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109},{"id":"2007.15646","title":"Rewriting a Deep Generative Model","created":"2020-07-30","cited_by_count":107},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93},{"id":"1808.10038","title":"Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds","created":"2018-08-29","cited_by_count":85},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60},{"id":"2302.03693","title":"Concept Algebra for (Score-Based) Text-Controlled Generative Models","created":"2023-02-07","cited_by_count":59},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55},{"id":"2103.14968","title":"Labels4Free: Unsupervised Segmentation using StyleGAN","created":"2021-03-27","cited_by_count":53},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50},{"id":"1906.10720","title":"Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics","created":"2019-06-25","cited_by_count":39},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39},{"id":"1503.00778","title":"Simple, Efficient, and Neural Algorithms for Sparse Coding","created":"2015-03-02","cited_by_count":37},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31},{"id":"1905.11071","title":"Learning step sizes for unfolded sparse coding","created":"2019-05-27","cited_by_count":30},{"id":"2306.05720","title":"Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model","created":"2023-06-09","cited_by_count":30},{"id":"2408.12578","title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","created":"2024-08-22","cited_by_count":26},{"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":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23},{"id":"2106.00058","title":"Stable and Interpretable Unrolled Dictionary Learning","created":"2021-05-31","cited_by_count":15},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15},{"id":"2410.01280","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","created":"2024-10-02","cited_by_count":15},{"id":"1411.2404","title":"The Johnson-Lindenstrauss lemma is optimal for linear dimensionality reduction","created":"2014-11-10","cited_by_count":12},{"id":"1708.03735","title":"Sparse Coding and Autoencoders","created":"2017-08-12","cited_by_count":11},{"id":"2106.06338","title":"Understanding approximate and unrolled dictionary learning for pattern recovery","created":"2021-06-11","cited_by_count":11},{"id":"2412.04619","title":"Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization","created":"2024-12-05","cited_by_count":10},{"id":"2504.08842","title":"Towards Combinatorial Interpretability of Neural Computation","created":"2025-04-10","cited_by_count":9},{"id":"2505.15970","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","created":"2025-05-21","cited_by_count":5}],"next_cursor":null}