{"total":23,"rows":[{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2510.23012","title":"Softmax is $1/2$-Lipschitz: A tight bound across all $\\ell_p$ norms","created":"2025-10-27","cited_by_count":22,"area":null},{"id":"2507.07814","title":"Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers","created":"2025-07-10","cited_by_count":11,"area":null},{"id":"2309.16883","title":"The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing","created":"2023-09-28","cited_by_count":8,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2212.14776","title":"On the Interpretability of Attention Networks","created":"2022-12-30","cited_by_count":5,"area":null},{"id":"2305.04722","title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2406.01189","title":"MultiMax: Sparse and Multi-Modal Attention Learning","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2112.05717","title":"Discourse-Aware Soft Prompting for Text Generation","created":"2021-12-10","cited_by_count":4,"area":null},{"id":"2101.07077","title":"Yet Another Representation of Binary Decision Trees: A Mathematical Demonstration","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2307.09321","title":"Exploiting Field Dependencies for Learning on Categorical Data","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2201.08676","title":"Distance-Ratio-Based Formulation for Metric Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2304.04275","title":"Filling out the missing gaps: Time Series Imputation with Semi-Supervised Learning","created":"2023-04-09","cited_by_count":1,"area":null},{"id":"2304.05243","title":"r-softmax: Generalized Softmax with Controllable Sparsity Rate","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2404.12768","title":"MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Models","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2608.02938","title":"When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2101.11347","title":"Decision Machines: Congruent Decision Trees","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2603.18712","title":"Accurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2610.15660","title":"Sparse All-Layer Connector for Domain Generalised Semantic Segmentation","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}