{"list":"other","total":90,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"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":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164},{"id":"2003.03384","title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","created":"2020-03-06","cited_by_count":143},{"id":"2007.01547","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","created":"2020-07-03","cited_by_count":119},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"1910.05446","title":"On Empirical Comparisons of Optimizers for Deep Learning","created":"2019-10-11","cited_by_count":103},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"1902.08295","title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","created":"2019-02-21","cited_by_count":86},{"id":"1709.07417","title":"Neural Optimizer Search with Reinforcement Learning","created":"2017-09-21","cited_by_count":82},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"2009.11243","title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves","created":"2020-09-23","cited_by_count":58},{"id":"1711.09268","title":"Generalizing Hamiltonian Monte Carlo with Neural Networks","created":"2017-11-25","cited_by_count":52},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"2002.03432","title":"On the distance between two neural networks and the stability of learning","created":"2020-02-09","cited_by_count":46},{"id":"2002.11803","title":"Disentangling Adaptive Gradient Methods from Learning Rates","created":"2020-02-26","cited_by_count":42},{"id":"1703.00441","title":"Learning to Optimize Neural Nets","created":"2017-03-01","cited_by_count":41},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32},{"id":"2010.09089","title":"Training Stronger Baselines for Learning to Optimize","created":"2020-10-18","cited_by_count":31},{"id":"2209.11208","title":"A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases","created":"2022-09-22","cited_by_count":30},{"id":"1909.09712","title":"Learning an Adaptive Learning Rate Schedule","created":"2019-09-20","cited_by_count":29},{"id":"2002.11887","title":"Using a thousand optimization tasks to learn hyperparameter search strategies","created":"2020-02-27","cited_by_count":29},{"id":"1911.03787","title":"Learning to Optimize in Swarms","created":"2019-11-09","cited_by_count":23},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"2004.12227","title":"Improved Adversarial Training via Learned Optimizer","created":"2020-04-25","cited_by_count":22},{"id":"1609.03759","title":"3D Simulation for Robot Arm Control with Deep Q-Learning","created":"2016-09-13","cited_by_count":21},{"id":"2002.09018","title":"Scalable Second Order Optimization for Deep Learning","created":"2020-02-20","cited_by_count":21},{"id":"2110.13572","title":"Periodic Activation Functions Induce Stationarity","created":"2021-10-26","cited_by_count":21},{"id":"1901.11150","title":"Memory-Efficient Adaptive Optimization","created":"2019-01-30","cited_by_count":19},{"id":"2011.02159","title":"Reverse engineering learned optimizers reveals known and novel mechanisms","created":"2020-11-04","cited_by_count":19},{"id":"1806.04522","title":"Meta-Learning for Stochastic Gradient MCMC","created":"2018-06-12","cited_by_count":16},{"id":"2106.04516","title":"Launchpad: A Programming Model for Distributed Machine Learning Research","created":"2021-06-07","cited_by_count":14},{"id":"2101.07367","title":"Training Learned Optimizers with Randomly Initialized Learned Optimizers","created":"2021-01-14","cited_by_count":13},{"id":"2107.09661","title":"Learn2Hop: Learned Optimization on Rough Landscapes","created":"2021-07-20","cited_by_count":12},{"id":"1906.03367","title":"Using learned optimizers to make models robust to input noise","created":"2019-06-08","cited_by_count":10},{"id":"2201.12426","title":"A Simple Guard for Learned Optimizers","created":"2022-01-28","cited_by_count":9}],"next_cursor":null}