{"list":"other","total":54,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"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":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"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":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"1711.03953","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","created":"2017-11-10","cited_by_count":152},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106},{"id":"1805.08315","title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","created":"2018-05-21","cited_by_count":98},{"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":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"1307.0468","title":"Discrete Signal Processing on Graphs: Frequency Analysis","created":"2013-07-01","cited_by_count":73},{"id":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63},{"id":"2006.16362","title":"Multi-Head Attention: Collaborate Instead of Concatenate","created":"2020-06-29","cited_by_count":60},{"id":"2211.08854","title":"Graph Filters for Signal Processing and Machine Learning on Graphs","created":"2022-11-16","cited_by_count":53},{"id":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32},{"id":"1906.01558","title":"Disentangling neural mechanisms for perceptual grouping","created":"2019-06-04","cited_by_count":28},{"id":"1606.08266","title":"Magnetic Eigenmaps for the Visualization of Directed Networks","created":"2016-06-27","cited_by_count":25},{"id":"2305.13571","title":"Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings","created":"2023-05-23","cited_by_count":23},{"id":"1606.07359","title":"Magnetic eigenmaps for community detection in directed networks","created":"2016-06-23","cited_by_count":22},{"id":"1412.7149","title":"Deep Fried Convnets","created":"2014-12-22","cited_by_count":21},{"id":"1511.05946","title":"ACDC: A Structured Efficient Linear Layer","created":"2015-11-18","cited_by_count":19},{"id":"2204.10670","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","created":"2022-04-22","cited_by_count":6}],"next_cursor":null}