{"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/attention-sinks/papers/ran/1","list_of":"/method/attention-sinks","method":"Attention Sinks","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,5],"of":5,"counts":{"archive_papers_tagged":13,"with_a_code_link":7,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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"},"first_page":"/method/attention-sinks/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/why-do-llms-attend-to-the-first-token","slug":"why-do-llms-attend-to-the-first-token","title":"Why do LLMs attend to the first token?","date":"2025-04-03","arxiv_id":"2504.02732","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/value-residual-learning-for-alleviating","slug":"value-residual-learning-for-alleviating","title":"Value Residual Learning For Alleviating Attention Concentration In Transformers","date":"2024-10-23","arxiv_id":"2410.17897","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Zcchill/Value-Residual-Learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/when-attention-sink-emerges-in-language","slug":"when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","arxiv_id":"2410.10781","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/attention-sink"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unveiling-and-harnessing-hidden-attention","slug":"unveiling-and-harnessing-hidden-attention","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","date":"2024-06-22","arxiv_id":"2406.15765","n_code_links":1,"syntology":{"ran":5,"of":13,"n_ran_checked":2,"n_instrument":3,"unverified":8,"pointer_only":13,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["gatech-eic/act"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-streaming-language-models-with","slug":"efficient-streaming-language-models-with","title":"Efficient Streaming Language Models with Attention Sinks","date":"2023-09-29","arxiv_id":"2309.17453","n_code_links":6,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":2,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["intel/intel-extension-for-transformers","mit-han-lab/streaming-llm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"1235f30e7c4090376b6163e9e6f837f05ec6e62dbca745fc6632d1f9b71f6a7a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}