{"list":"other","total":64,"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":"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"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":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1302.4245","title":"Gaussian Process Kernels for Pattern Discovery and Extrapolation","created":"2013-02-18","cited_by_count":132},{"id":"1901.03429","title":"On the Turing Completeness of Modern Neural Network Architectures","created":"2019-01-10","cited_by_count":129},{"id":"2004.03497","title":"ProGen: Language Modeling for Protein Generation","created":"2020-03-08","cited_by_count":128},{"id":"2004.11154","title":"Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond","created":"2020-04-23","cited_by_count":109},{"id":"2103.05180","title":"An Introduction to Deep Generative Modeling","created":"2021-03-09","cited_by_count":104},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"1506.02785","title":"On the Error of Random Fourier Features","created":"2015-06-09","cited_by_count":76},{"id":"1805.12462","title":"On GANs and GMMs","created":"2018-05-31","cited_by_count":62},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60},{"id":"2106.06899","title":"Memory-efficient Transformers via Top-$k$ Attention","created":"2021-06-13","cited_by_count":60},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51},{"id":"1703.00864","title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","created":"2017-03-02","cited_by_count":45},{"id":"1412.8293","title":"Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels","created":"2014-12-29","cited_by_count":42},{"id":"1705.08736","title":"Non-Stationary Spectral Kernels","created":"2017-05-24","cited_by_count":38},{"id":"1911.04070","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","created":"2019-11-11","cited_by_count":38},{"id":"2004.08483","title":"ETC: Encoding Long and Structured Inputs in Transformers","created":"2020-04-17","cited_by_count":34},{"id":"2109.15142","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","created":"2021-09-30","cited_by_count":31},{"id":"1809.04481","title":"But How Does It Work in Theory? Linear SVM with Random Features","created":"2018-09-12","cited_by_count":28},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26},{"id":"2110.04367","title":"Hybrid Random Features","created":"2021-10-08","cited_by_count":25},{"id":"1709.02605","title":"Gaussian Quadrature for Kernel Features","created":"2017-09-08","cited_by_count":21},{"id":"1412.6493","title":"A la Carte - Learning Fast Kernels","created":"2014-12-19","cited_by_count":18},{"id":"1506.02236","title":"Generalized Spectral Kernels","created":"2015-06-07","cited_by_count":17},{"id":"2109.02377","title":"PermuteFormer: Efficient Relative Position Encoding for Long Sequences","created":"2021-09-06","cited_by_count":14},{"id":"1902.10214","title":"Implicit Kernel Learning","created":"2019-02-26","cited_by_count":13},{"id":"1506.08776","title":"Bayesian Nonparametric Kernel-Learning","created":"2015-06-29","cited_by_count":10},{"id":"1605.09049","title":"Recycling Randomness with Structure for Sublinear time Kernel Expansions","created":"2016-05-29","cited_by_count":9},{"id":"1311.0914","title":"A Divide-and-Conquer Solver for Kernel Support Vector Machines","created":"2013-11-04","cited_by_count":8},{"id":"1810.04416","title":"Harmonizable mixture kernels with variational Fourier features","created":"2018-10-10","cited_by_count":8},{"id":"1808.10724","title":"Learning Data-adaptive Nonparametric Kernels","created":"2018-08-31","cited_by_count":7},{"id":"2009.04614","title":"End-to-end Kernel Learning via Generative Random Fourier Features","created":"2020-09-10","cited_by_count":7},{"id":"1710.10230","title":"Not-So-Random Features","created":"2017-10-27","cited_by_count":5}],"next_cursor":null}