{"list":"other","total":59,"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"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":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"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":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"1901.10430","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","created":"2019-01-29","cited_by_count":211},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"1610.06258","title":"Using Fast Weights to Attend to the Recent Past","created":"2016-10-20","cited_by_count":170},{"id":"1911.02972","title":"Blockwise Self-Attention for Long Document Understanding","created":"2019-11-07","cited_by_count":159},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"1809.01576","title":"Document-Level Neural Machine Translation with Hierarchical Attention Networks","created":"2018-09-05","cited_by_count":85},{"id":"1804.02464","title":"Differentiable plasticity: training plastic neural networks with backpropagation","created":"2018-04-06","cited_by_count":84},{"id":"1711.04956","title":"Classical Structured Prediction Losses for Sequence to Sequence Learning","created":"2017-11-14","cited_by_count":55},{"id":"1611.03220","title":"Faster Kernel Ridge Regression Using Sketching and Preconditioning","created":"2016-11-10","cited_by_count":44},{"id":"1904.11660","title":"Transformers with convolutional context for ASR","created":"2019-04-26","cited_by_count":44},{"id":"1412.8293","title":"Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels","created":"2014-12-29","cited_by_count":42},{"id":"2005.00742","title":"Hard-Coded Gaussian Attention for Neural Machine Translation","created":"2020-05-02","cited_by_count":42},{"id":"1907.10747","title":"Sampled Softmax with Random Fourier Features","created":"2019-07-24","cited_by_count":33},{"id":"1904.03092","title":"Modeling Recurrence for Transformer","created":"2019-04-05","cited_by_count":26},{"id":"2005.06537","title":"A Mixture of $h-1$ Heads is Better than $h$ Heads","created":"2020-05-13","cited_by_count":22},{"id":"1808.09357","title":"Rational Recurrences","created":"2018-08-28","cited_by_count":18},{"id":"1410.7414","title":"Fast Function to Function Regression","created":"2014-10-27","cited_by_count":7},{"id":"1910.12554","title":"Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification","created":"2019-10-28","cited_by_count":3}],"next_cursor":null}