{"list":"other","total":76,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"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":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1712.09482","title":"Robust Loss Functions under Label Noise for Deep Neural Networks","created":"2017-12-27","cited_by_count":443},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"1901.09321","title":"Fixup Initialization: Residual Learning Without Normalization","created":"2019-01-27","cited_by_count":198},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"1405.5869","title":"Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)","created":"2014-05-22","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":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102},{"id":"1912.05170","title":"Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey","created":"2019-12-11","cited_by_count":101},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80},{"id":"1810.09619","title":"Sparse DNNs with Improved Adversarial Robustness","created":"2018-10-23","cited_by_count":72},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68},{"id":"2106.06899","title":"Memory-efficient Transformers via Top-$k$ Attention","created":"2021-06-13","cited_by_count":60},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57},{"id":"2106.09276","title":"Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting","created":"2021-06-17","cited_by_count":54},{"id":"1607.08194","title":"Convolutional Neural Networks Analyzed via Convolutional Sparse Coding","created":"2016-07-27","cited_by_count":52},{"id":"2012.05420","title":"On the emergence of simplex symmetry in the final and penultimate layers of neural network classifiers","created":"2020-12-10","cited_by_count":52},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50},{"id":"1411.3230","title":"Sparse Modeling for Image and Vision Processing","created":"2014-11-12","cited_by_count":48},{"id":"1903.03129","title":"SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems","created":"2019-03-07","cited_by_count":46},{"id":"1903.11257","title":"How Can We Be So Dense? The Benefits of Using Highly Sparse Representations","created":"2019-03-27","cited_by_count":45},{"id":"1312.4461","title":"Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networks","created":"2013-12-16","cited_by_count":44},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"id":"2006.16992","title":"Deep Isometric Learning for Visual Recognition","created":"2020-06-30","cited_by_count":39},{"id":"1705.01626","title":"Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks","created":"2017-05-03","cited_by_count":37},{"id":"2101.00072","title":"Explicit regularization and implicit bias in deep network classifiers trained with the square loss","created":"2020-12-31","cited_by_count":37},{"id":"1812.04056","title":"Accelerating Convolutional Neural Networks via Activation Map Compression","created":"2018-12-10","cited_by_count":34},{"id":"2006.08857","title":"Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization","created":"2020-06-16","cited_by_count":26},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24},{"id":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23},{"id":"2203.03597","title":"Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias","created":"2022-03-07","cited_by_count":22},{"id":"2012.00807","title":"On the robustness of minimum norm interpolators and regularized empirical risk minimizers","created":"2020-12-01","cited_by_count":19},{"id":"2206.14286","title":"TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s","created":"2022-06-28","cited_by_count":18},{"id":"2110.02802","title":"Self-conditioning pre-trained language models","created":"2021-09-30","cited_by_count":16},{"id":"1708.08705","title":"Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning","created":"2017-08-29","cited_by_count":14},{"id":"2110.09548","title":"Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks","created":"2021-10-18","cited_by_count":14},{"id":"2202.13216","title":"Adversarial robustness of sparse local Lipschitz predictors","created":"2022-02-26","cited_by_count":11},{"id":"2204.09664","title":"Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?","created":"2022-04-20","cited_by_count":10},{"id":"2104.00008","title":"Why is AI hard and Physics simple?","created":"2021-03-31","cited_by_count":7},{"id":"2006.06179","title":"Recovery and Generalization in Over-Realized Dictionary Learning","created":"2020-06-11","cited_by_count":6},{"id":"2208.04461","title":"A Theoretical View on Sparsely Activated Networks","created":"2022-08-08","cited_by_count":6}],"next_cursor":null}