{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"1606.01865","title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values","created":"2016-06-06","cited_by_count":554},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"1611.06455","title":"Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline","created":"2016-11-20","cited_by_count":360},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"1803.09820","title":"A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay","created":"2018-03-26","cited_by_count":226},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"1902.08730","title":"AliGraph: A Comprehensive Graph Neural Network Platform","created":"2019-02-23","cited_by_count":153},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2001.08317","title":"Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case","created":"2020-01-23","cited_by_count":129},{"id":"1711.03905","title":"Attend and Diagnose: Clinical Time Series Analysis using Attention Models","created":"2017-11-10","cited_by_count":105},{"id":"1804.00247","title":"Training Tips for the Transformer Model","created":"2018-04-01","cited_by_count":85},{"id":"2011.01843","title":"Tabular Transformers for Modeling Multivariate Time Series","created":"2020-11-03","cited_by_count":77},{"id":"1811.10166","title":"Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series","created":"2018-11-26","cited_by_count":76},{"id":"1910.10536","title":"Self-attention for raw optical Satellite Time Series Classification","created":"2019-10-23","cited_by_count":75},{"id":"2002.11794","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","created":"2020-02-26","cited_by_count":67},{"id":"2103.14438","title":"Gated Transformer Networks for Multivariate Time Series Classification","created":"2021-03-26","cited_by_count":58},{"id":"1904.07418","title":"Positional Encoding to Control Output Sequence Length","created":"2019-04-16","cited_by_count":56},{"id":"2010.04903","title":"What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding","created":"2020-10-10","cited_by_count":52},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48},{"id":"2012.15355","title":"Optimizing Deeper Transformers on Small Datasets","created":"2020-12-30","cited_by_count":42},{"id":"1802.06467","title":"Memorize or generalize? Searching for a compositional RNN in a haystack","created":"2018-02-18","cited_by_count":41},{"id":"1907.05572","title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","created":"2019-07-12","cited_by_count":39},{"id":"1808.07561","title":"Training Deeper Neural Machine Translation Models with Transparent Attention","created":"2018-08-22","cited_by_count":38},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38},{"id":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37},{"id":"1904.03092","title":"Modeling Recurrence for Transformer","created":"2019-04-05","cited_by_count":26},{"id":"1809.07589","title":"DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn","created":"2018-09-20","cited_by_count":14},{"id":"1610.02583","title":"A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation","created":"2016-10-08","cited_by_count":12},{"id":"2106.15850","title":"Exploring Robust Architectures for Deep Artificial Neural Networks","created":"2021-06-30","cited_by_count":11},{"id":"2110.08255","title":"Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting","created":"2021-10-13","cited_by_count":11},{"id":"2109.08381","title":"From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba","created":"2021-09-17","cited_by_count":10},{"id":"2102.05624","title":"NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting","created":"2021-02-10","cited_by_count":8},{"id":"2108.12784","title":"TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting","created":"2021-08-29","cited_by_count":8},{"id":"1710.01278","title":"Dilated Convolutions for Modeling Long-Distance Genomic Dependencies","created":"2017-10-03","cited_by_count":7},{"id":"2110.01825","title":"Attention Augmented Convolutional Transformer for Tabular Time-series","created":"2021-10-05","cited_by_count":4}],"next_cursor":null}