{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"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":"1501.01571","title":"An Introduction to Matrix Concentration Inequalities","created":"2015-01-07","cited_by_count":397},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1802.05814","title":"Variational Autoencoders for Collaborative Filtering","created":"2018-02-16","cited_by_count":310},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100},{"id":"2202.13556","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","created":"2022-02-28","cited_by_count":96},{"id":"1910.00762","title":"Accelerating Deep Learning by Focusing on the Biggest Losers","created":"2019-10-02","cited_by_count":94},{"id":"1910.01727","title":"Generalized Inner Loop Meta-Learning","created":"2019-10-03","cited_by_count":93},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"1901.01151","title":"Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision","created":"2019-01-03","cited_by_count":64},{"id":"2007.01357","title":"Efficient computation and analysis of distributional Shapley values","created":"2020-07-02","cited_by_count":38},{"id":"2108.00261","title":"ECLARE: Extreme Classification with Label Graph Correlations","created":"2021-07-31","cited_by_count":38},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38},{"id":"2304.07718","title":"Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value","created":"2023-04-16","cited_by_count":38},{"id":"1811.09975","title":"Sequential Variational Autoencoders for Collaborative Filtering","created":"2018-11-25","cited_by_count":31},{"id":"1906.04845","title":"Discrepancy, Coresets, and Sketches in Machine Learning","created":"2019-06-11","cited_by_count":30},{"id":"2206.02626","title":"Infinite Recommendation Networks: A Data-Centric Approach","created":"2022-06-03","cited_by_count":20},{"id":"2010.09654","title":"Semi-supervised Batch Active Learning via Bilevel Optimization","created":"2020-10-19","cited_by_count":16},{"id":"2002.03503","title":"Regularized Submodular Maximization at Scale","created":"2020-02-10","cited_by_count":15},{"id":"2107.04984","title":"SVP-CF: Selection via Proxy for Collaborative Filtering Data","created":"2021-07-11","cited_by_count":14},{"id":"2201.04768","title":"On Sampling Collaborative Filtering Datasets","created":"2022-01-13","cited_by_count":8}],"next_cursor":null}