{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1705.08584","title":"MMD GAN: Towards Deeper Understanding of Moment Matching Network","created":"2017-05-24","cited_by_count":254},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"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":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126},{"id":"1706.02262","title":"InfoVAE: Information Maximizing Variational Autoencoders","created":"2017-06-07","cited_by_count":124},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"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":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"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":"2002.11603","title":"DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation","created":"2020-02-26","cited_by_count":78},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46},{"id":"2303.04707","title":"DiM: Distilling Dataset into Generative Model","created":"2023-03-08","cited_by_count":46},{"id":"2502.20653","title":"Dataset Distillation with Neural Characteristic Function: A Minmax Perspective","created":"2025-02-28","cited_by_count":45},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34},{"id":"2303.04449","title":"Loss-Curvature Matching for Dataset Selection and Condensation","created":"2023-03-08","cited_by_count":33},{"id":"2305.01975","title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","created":"2023-05-03","cited_by_count":32},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31},{"id":"2406.10485","title":"A Label is Worth a Thousand Images in Dataset Distillation","created":"2024-06-15","cited_by_count":31},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26},{"id":"2403.10045","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","created":"2024-03-15","cited_by_count":17},{"id":"2207.11727","title":"Can we achieve robustness from data alone?","created":"2022-07-24","cited_by_count":16},{"id":"2309.07698","title":"Dataset Condensation via Generative Model","created":"2023-09-14","cited_by_count":15},{"id":"2408.16236","title":"Neural Spectral Decomposition for Dataset Distillation","created":"2024-08-29","cited_by_count":14},{"id":"2410.07579","title":"Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching","created":"2024-10-10","cited_by_count":13},{"id":"2211.10752","title":"Towards Robust Dataset Learning","created":"2022-11-19","cited_by_count":9},{"id":"1707.04319","title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","created":"2017-07-13","cited_by_count":8},{"id":"1707.01209","title":"Model compression as constrained optimization, with application to neural nets. Part I: general framework","created":"2017-07-05","cited_by_count":6},{"id":"2310.15052","title":"DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching","created":"2023-10-23","cited_by_count":6},{"id":"2402.05675","title":"Is Adversarial Training with Compressed Datasets Effective?","created":"2024-02-08","cited_by_count":1}],"next_cursor":null}