{"total":21,"rows":[{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2401.00423","title":"MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting","created":"2023-12-31","cited_by_count":50,"area":null},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44,"area":null},{"id":"2303.08433","title":"The Benefits of Mixup for Feature Learning","created":"2023-03-15","cited_by_count":19,"area":null},{"id":"2311.02883","title":"SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data","created":"2023-11-06","cited_by_count":16,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2306.01271","title":"On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2406.03944","title":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2510.17526","title":"How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2310.04674","title":"ReactionTeam: Teaming Experts for Divergent Thinking Beyond Typical Reaction Patterns","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2301.05865","title":"Gated Self-supervised Learning For Improving Supervised Learning","created":"2023-01-14","cited_by_count":1,"area":null},{"id":"2310.12143","title":"Simple Mechanisms for Representing, Indexing and Manipulating Concepts","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2410.03497","title":"Collaborative and Efficient Personalization with Mixtures of Adaptors","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.23608","title":"Context-Aware Token Selection and Packing for Enhanced Vision Transformer","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2509.00102","title":"ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Models","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2302.00003","title":"The Power of External Memory in Increasing Predictive Model Capacity","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2305.02899","title":"Additive Class Distinction Maps using Branched-GANs","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2406.10771","title":"Predicting Exoplanetary Features with a Residual Model for Uniform and Gaussian Distributions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2406.16741","title":"Extracting thin film structures of energy materials using transformers","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2502.13873","title":"NVR: Vector Runahead on NPUs for Sparse Memory Access","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2603.29200","title":"Improving Ensemble Forecasts of Abnormally Deflecting Tropical Cyclones with Fused Atmosphere-Ocean-Terrain Data","created":"2026-03-31","cited_by_count":0,"area":null}],"next_cursor":null}