{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138},{"id":"1702.03275","title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","created":"2017-02-10","cited_by_count":128},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"id":"2407.15138","title":"D$^4$M: Dataset Distillation via Disentangled Diffusion Model","created":"2024-07-21","cited_by_count":77},{"id":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69},{"id":"1809.00846","title":"Towards Understanding Regularization in Batch Normalization","created":"2018-09-04","cited_by_count":56},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","cited_by_count":35},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26},{"id":"2406.18561","title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","created":"2024-05-28","cited_by_count":22},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2410.15919","title":"Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?","created":"2024-10-21","cited_by_count":19},{"id":"2506.23580","title":"Dataset Distillation via Vision-Language Category Prototype","created":"2025-06-30","cited_by_count":19},{"id":"2401.15863","title":"Importance-Aware Adaptive Dataset Distillation","created":"2024-01-29","cited_by_count":18},{"id":"2505.24623","title":"Hyperbolic Dataset Distillation","created":"2025-05-30","cited_by_count":15},{"id":"2501.07575","title":"Dataset Distillation via Committee Voting","created":"2025-01-13","cited_by_count":14},{"id":"2406.05704","title":"Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation","created":"2024-06-09","cited_by_count":13},{"id":"2506.24125","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","created":"2025-06-30","cited_by_count":11},{"id":"2507.04619","title":"Information-Guided Diffusion Sampling for Dataset Distillation","created":"2025-07-07","cited_by_count":10},{"id":"2312.08912","title":"Dataset Distillation via Adversarial Prediction Matching","created":"2023-12-14","cited_by_count":9},{"id":"2507.03331","title":"Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling","created":"2025-07-04","cited_by_count":8},{"id":"2511.17890","title":"Decoupled Audio-Visual Dataset Distillation","created":"2025-11-22","cited_by_count":7},{"id":"2603.07476","title":"EVLF: Early Vision-Language Fusion for Generative Dataset Distillation","created":"2026-03-08","cited_by_count":4},{"id":"2512.08317","title":"GeoDM: Geometry-aware Distribution Matching for Dataset Distillation","created":"2025-12-09","cited_by_count":3},{"id":"2512.15647","title":"Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift","created":"2025-12-17","cited_by_count":1},{"id":"2607.00916","title":"Condensing Large-Scale Datasets Directly with Minimal Information Loss","created":"2026-07-01","cited_by_count":1}],"next_cursor":null}