{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/mixed-attention-block","slug":"mixed-attention-block","name":"Mixed Attention Block","full_name":"Mixed Attention Block","full_name_withheld":false,"description_markdown":"**Mixed Attention Block** is an attention module used in the [ConvBERT](https://paperswithcode.com/method/convbert) architecture. It is a mixture of [self-attention](https://paperswithcode.com/method/scaled) and [span-based dynamic convolution](https://paperswithcode.com/method/span-based-dynamic-convolution) (highlighted in pink). They share the same Query but use different Key to generate the attention map and [convolution](https://paperswithcode.com/method/convolution) kernel respectively. The number of attention heads is reducing by directly projecting the input to a smaller embedding space to form a bottleneck structure for self-attention and span-based dynamic convolution. Dimensions of the input and output of some blocks are labeled on the left top corner to illustrate the overall framework, where $d$ is the embedding size of the input and $\\gamma$ is the reduction ratio.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","paper":"/paper/convbert-improving-bert-with-span-based","first_author":"Zi-Hang Jiang","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/convbert-improving-bert-with-span-based"},"source":{"url":"https://arxiv.org/abs/2008.02496v3","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Attention Modules","url":"/methods/category/attention-modules","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"slug":"beyond-simple-concatenation-fairly-assessing","title":"Beyond Simple Concatenation: Fairly Assessing PLM Architectures for Multi-Chain Protein-Protein Interactions Prediction","date":"2025-05-26","arxiv_id":"2505.20036","n_code_links":0,"syntology":null},{"paper":"/paper/navigating-nuance-in-quest-for-political","slug":"navigating-nuance-in-quest-for-political","title":"Navigating Nuance: In Quest for Political Truth","date":"2025-01-01","arxiv_id":"2501.00782","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-v-s-media-bias-a-comparative-study-of","title":"ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models","date":"2024-03-29","arxiv_id":"2403.20158","n_code_links":0,"syntology":null},{"paper":"/paper/m-3-net-multilevel-mixed-and-multistage","slug":"m-3-net-multilevel-mixed-and-multistage","title":"M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection","date":"2023-09-15","arxiv_id":"2309.08365","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-punctuation-restoration-for","slug":"transformer-based-punctuation-restoration-for","title":"Transformer Based Punctuation Restoration for Turkish","date":"2023-09-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/convbert-improving-bert-with-span-based","slug":"convbert-improving-bert-with-span-based","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","date":"2020-08-06","arxiv_id":"2008.02496","n_code_links":8,"syntology":null}],"papers_shown":6,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":6,"with_a_code_link":4,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/bias-detection","name":"Bias Detection","papers":1},{"task":"/task/drug-discovery","name":"Drug Discovery","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/misinformation","name":"Misinformation","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/punctuation-restoration","name":"Punctuation Restoration","papers":1},{"task":"/task/salient-object-detection","name":"RGB Salient Object Detection","papers":1},{"task":"/task/salient-object-detection-1","name":"Salient Object Detection","papers":1},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":1}],"tasks_shown":16,"n_tasks":16,"usage_by_year":[{"year":"2020","papers":1},{"year":"2023","papers":2},{"year":"2024","papers":1},{"year":"2025","papers":2}],"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/mixed-attention-block"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Mixed%20Attention%20Block","read_at":"2026-10-05T00:59:08+00:00","query":"Mixed Attention Block","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2008.02496","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Mixed Attention Block' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Diagonal-Tiled Mixed-Precision Attention (DMA)","A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention","Mixed-CUTS","mixed-play","EL-Attention","VC-Attention","TF-ATTENTION","SS-Attention"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"34c31eab7de605742bae4b93240bd0fa34ab203b4481d386d81355c7d0363d7a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}