{"url":"/method/rsu-benes-block","slug":"rsu-benes-block","name":"RSU Beneš Block","full_name":"Beneš Block with Residual Switch Units","full_name_withheld":false,"description_markdown":"The **Beneš block** is a computation-efficient alternative to dense attention, enabling the modelling of long-range dependencies in O(n log n) time. In comparison, dense attention which is commonly used in Transformers has O(n^2) complexity.\r\n\r\nIn music, dependencies occur on several scales, including on a coarse scale which requires processing very long sequences. Beneš blocks have been used in Residual Shuffle-Exchange Networks to achieve state-of-the-art results in music transcription.\r\n\r\nBeneš blocks have a ‘receptive field’ of the size of the whole sequence, and it has no bottleneck. These properties hold for dense attention but have not been shown for many sparse attention and dilated convolutional architectures.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","paper":"/paper/residual-shuffle-exchange-networks-for-fast","first_author":"Andis Draguns","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/residual-shuffle-exchange-networks-for-fast"},"source":{"url":"https://arxiv.org/abs/2004.04662v4","title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Audio","area_id":"audio","collection":"Audio Model Blocks","url":"/methods/category/audio-model-blocks","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"title":"Nash Equilibrium Between Consumer Electronic Devices and DoS Attacker for Distributed IoT-enabled RSE Systems","date":"2025-04-13","arxiv_id":"2504.09415","n_code_links":0,"syntology":null},{"paper":null,"title":"The radius of statistical efficiency","date":"2024-05-15","arxiv_id":"2405.09676","n_code_links":0,"syntology":null},{"paper":null,"title":"A Multi-Modal Machine Learning Approach to Detect Extreme Rainfall Events in Sicily","date":"2022-12-14","arxiv_id":"2212.08102","n_code_links":0,"syntology":null},{"paper":null,"title":"Attack-Resilient State Estimation with Intermittent Data Authentication","date":"2020-05-16","arxiv_id":"2005.08122","n_code_links":0,"syntology":null},{"paper":"/paper/residual-shuffle-exchange-networks-for-fast","title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","date":"2020-04-06","arxiv_id":"2004.04662","n_code_links":2,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/state-estimation","name":"State Estimation","papers":2},{"task":"/task/lambada","name":"LAMBADA","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/matrix-completion","name":"Matrix Completion","papers":1},{"task":"/task/music-transcription","name":"Music Transcription","papers":1},{"task":"/task/q-learning","name":"Q-Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2020","papers":2},{"year":"2022","papers":1},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/rsu-benes-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}