{"list":"other","total":55,"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":"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"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":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"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":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1608.05859","title":"Using the Output Embedding to Improve Language Models","created":"2016-08-20","cited_by_count":272},{"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":"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":"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":"1907.05242","title":"Large Memory Layers with Product Keys","created":"2019-07-10","cited_by_count":124},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"1611.01462","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","created":"2016-11-04","cited_by_count":92},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"2006.11527","title":"Memory Transformer","created":"2020-06-20","cited_by_count":76},{"id":"2012.15832","title":"Shortformer: Better Language Modeling using Shorter Inputs","created":"2020-12-31","cited_by_count":76},{"id":"2004.12744","title":"Augmenting Transformers with KNN-Based Composite Memory for Dialogue","created":"2020-04-27","cited_by_count":53}],"next_cursor":null}