{"list":"other","total":73,"rows":[{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2005.08926","title":"Neural Controlled Differential Equations for Irregular Time Series","created":"2020-05-18","cited_by_count":506},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2102.01010","title":"Machine learning accelerated computational fluid dynamics","created":"2021-01-28","cited_by_count":471},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2001.04385","title":"Universal Differential Equations for Scientific Machine Learning","created":"2020-01-13","cited_by_count":353},{"id":"1704.00447","title":"Learning a Variational Network for Reconstruction of Accelerated MRI Data","created":"2017-04-03","cited_by_count":342},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"2105.14080","title":"Gotta Go Fast When Generating Data with Score-Based Models","created":"2021-05-28","cited_by_count":219},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1911.08655","title":"Towards Physics-informed Deep Learning for Turbulent Flow Prediction","created":"2019-11-20","cited_by_count":204},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"1906.02773","title":"One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers","created":"2019-06-06","cited_by_count":102},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"1904.01112","title":"Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction","created":"2019-04-01","cited_by_count":81},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"1903.05895","title":"Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations","created":"2019-03-14","cited_by_count":76},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2006.12156","title":"Logarithmic Pruning is All You Need","created":"2020-06-22","cited_by_count":71},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58},{"id":"2102.06103","title":"Measuring Robustness in Deep Learning Based Compressive Sensing","created":"2021-02-11","cited_by_count":53},{"id":"2203.06823","title":"SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation","created":"2022-03-14","cited_by_count":44},{"id":"1510.01722","title":"Structured Transforms for Small-Footprint Deep Learning","created":"2015-10-06","cited_by_count":42},{"id":"2012.14966","title":"Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps","created":"2020-12-29","cited_by_count":36},{"id":"2008.13006","title":"Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity","created":"2020-08-29","cited_by_count":34},{"id":"2007.09601","title":"Hypersolvers: Toward Fast Continuous-Depth Models","created":"2020-07-19","cited_by_count":33},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"1802.03832","title":"Quadrature-based features for kernel approximation","created":"2018-02-11","cited_by_count":26},{"id":"2008.13065","title":"Unsupervised MRI Reconstruction with Generative Adversarial Networks","created":"2020-08-29","cited_by_count":24},{"id":"2106.03885","title":"Differentiable Multiple Shooting Layers","created":"2021-06-07","cited_by_count":20},{"id":"1511.05946","title":"ACDC: A Structured Efficient Linear Layer","created":"2015-11-18","cited_by_count":19},{"id":"1810.02309","title":"Learning Compressed Transforms with Low Displacement Rank","created":"2018-10-04","cited_by_count":19},{"id":"1910.09116","title":"Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Data","created":"2019-10-21","cited_by_count":17},{"id":"1906.02256","title":"Butterfly Transform: An Efficient FFT Based Neural Architecture Design","created":"2019-06-05","cited_by_count":16},{"id":"2111.02549","title":"VORTEX: Physics-Driven Data Augmentations Using Consistency Training for Robust Accelerated MRI Reconstruction","created":"2021-11-03","cited_by_count":16},{"id":"2007.08864","title":"Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice","created":"2020-07-17","cited_by_count":9},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8},{"id":"1611.04069","title":"Low-rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging","created":"2016-11-13","cited_by_count":6},{"id":"1506.07300","title":"Flexible Multi-layer Sparse Approximations of Matrices and Applications","created":"2015-06-24","cited_by_count":5},{"id":"1507.08751","title":"Beyond Low Rank + Sparse: Multi-scale Low Rank Matrix Decomposition","created":"2015-07-31","cited_by_count":5},{"id":"2104.05028","title":"Blind Primed Supervised (BLIPS) Learning for MR Image Reconstruction","created":"2021-04-11","cited_by_count":5},{"id":"2109.08184","title":"Sparse Factorization of Large Square Matrices","created":"2021-09-16","cited_by_count":2},{"id":"2010.06305","title":"Approximate Simultaneous Diagonalization of Matrices via Structured Low-Rank Approximation","created":"2020-10-13","cited_by_count":1}],"next_cursor":null}