{"list":"other","total":63,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"1909.06312","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","created":"2019-09-13","cited_by_count":203},{"id":"1708.07120","title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","created":"2017-08-23","cited_by_count":199},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1907.05242","title":"Large Memory Layers with Product Keys","created":"2019-07-10","cited_by_count":124},{"id":"2004.00070","title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","created":"2020-03-31","cited_by_count":115},{"id":"1509.02897","title":"Practical and Optimal LSH for Angular Distance","created":"2015-09-09","cited_by_count":106},{"id":"2002.10137","title":"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose","created":"2020-02-24","cited_by_count":92},{"id":"1810.07770","title":"Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity","created":"2018-10-17","cited_by_count":78},{"id":"1909.12778","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","created":"2019-09-27","cited_by_count":70},{"id":"1810.09665","title":"A jamming transition from under- to over-parametrization affects loss landscape and generalization","created":"2018-10-22","cited_by_count":67},{"id":"1703.03129","title":"Learning to Remember Rare Events","created":"2017-03-09","cited_by_count":63},{"id":"2002.09518","title":"Memory-Based Graph Networks","created":"2020-02-21","cited_by_count":56},{"id":"1312.4461","title":"Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networks","created":"2013-12-16","cited_by_count":44},{"id":"1711.02604","title":"Unbounded cache model for online language modeling with open vocabulary","created":"2017-11-07","cited_by_count":37},{"id":"1802.02422","title":"Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors","created":"2018-02-07","cited_by_count":37},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1906.11888","title":"Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks","created":"2019-06-09","cited_by_count":32},{"id":"1807.02264","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments","created":"2018-07-06","cited_by_count":30},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"1406.7362","title":"Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning","created":"2014-06-28","cited_by_count":24},{"id":"1803.01500","title":"Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks","created":"2018-03-05","cited_by_count":12},{"id":"1911.03898","title":"Understanding Multi-Head Attention in Abstractive Summarization","created":"2019-11-10","cited_by_count":12},{"id":"1603.04614","title":"Scalable Image Retrieval by Sparse Product Quantization","created":"2016-03-15","cited_by_count":2}],"next_cursor":null}