{"list":"other","total":54,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2012.00926","title":"pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis","created":"2020-12-02","cited_by_count":708},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1505.00387","title":"Highway Networks","created":"2015-05-03","cited_by_count":260},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"1811.02017","title":"A General Theory of Equivariant CNNs on Homogeneous Spaces","created":"2018-11-05","cited_by_count":228},{"id":"1705.07761","title":"VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning","created":"2017-05-22","cited_by_count":200},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"1908.06315","title":"Implicit Deep Learning","created":"2019-08-17","cited_by_count":124},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2005.12900","title":"Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model","created":"2020-05-26","cited_by_count":109},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84},{"id":"1712.02779","title":"Exploring the Landscape of Spatial Robustness","created":"2017-12-07","cited_by_count":81},{"id":"1404.3606","title":"PCANet: A Simple Deep Learning Baseline for Image Classification?","created":"2014-04-14","cited_by_count":70},{"id":"2006.12373","title":"Learning Physical Graph Representations from Visual Scenes","created":"2020-06-22","cited_by_count":50},{"id":"1512.06293","title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction","created":"2015-12-19","cited_by_count":46},{"id":"2106.10151","title":"The Dimpled Manifold Model of Adversarial Examples in Machine Learning","created":"2021-06-18","cited_by_count":41},{"id":"2008.11245","title":"Deep Networks and the Multiple Manifold Problem","created":"2020-08-25","cited_by_count":35},{"id":"1710.05488","title":"A Geometric View of Optimal Transportation and Generative Model","created":"2017-10-16","cited_by_count":31},{"id":"1906.01217","title":"Convergence of Learning Dynamics in Stackelberg Games","created":"2019-06-04","cited_by_count":28},{"id":"1905.11092","title":"A Rate-Distortion Framework for Explaining Neural Network Decisions","created":"2019-05-27","cited_by_count":24},{"id":"2111.06636","title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","created":"2021-11-12","cited_by_count":17},{"id":"2202.05411","title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","created":"2022-02-11","cited_by_count":17},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6},{"id":"2204.00077","title":"Efficient Maximal Coding Rate Reduction by Variational Forms","created":"2022-03-31","cited_by_count":6},{"id":"2206.09120","title":"Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games","created":"2022-06-18","cited_by_count":4}],"next_cursor":null}