{"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":"/paper/an-evolved-universal-transformer-memory","title":"An Evolved Universal Transformer Memory","arxiv_id":"2410.13166","date":"2024-10-17","proceeding":null,"authors":["Edoardo Cetin","Qi Sun","Tianyu Zhao","Yujin Tang"],"abstract":"Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable to any model using self-attention as they condition exclusively on the values in the produced attention matrices. Learning NAMMs on a small set of problems, we achieve substantial performance improvements across multiple long-context benchmarks while cutting the model's input contexts up to a fraction of the original sizes. We show the generality of our conditioning enables zero-shot transfer of NAMMs trained only on language to entirely new transformer architectures even across input modalities, with their benefits carrying over to vision and reinforcement learning.","url_abs":"https://arxiv.org/abs/2410.13166v3","url_pdf":"https://arxiv.org/pdf/2410.13166v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-evolved-universal-transformer-memory","repo_url":"https://github.com/sakanaai/evo-memory","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.13166","atlas_url":"https://app.syntology.ai/?focus=2410.13166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13166"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.13166"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.13166"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.13166\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.13166"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.13166\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.13166"},"call":"get_concepts_for_paper(arxiv_id=\"2410.13166\")"}],"by_repo":[{"repo":"sakanaai/evo-memory","kind":"official","samples":12,"ran":11,"instrument":2,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.13166.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.13166.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/SakanaAI/evo-memory","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sakanaai/evo-memory","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":5,"ran_violates":3,"ran_draft_wrong":2,"unverified":1},"n_samples":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":12,"ran":11,"n_ran_checked":9,"n_instrument":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":12,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":11,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"8979b56a0788125e","code_sha256_prefix":"8979b56a0788125e","entry":"compute_recency","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_dynamic.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_dynamic.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"position_ids:Tensor/2/int, start_recency_from:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8979b56a0788125e"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"8979b56a0788125e"}},{"code_sha256":"b138114d7116560c","code_sha256_prefix":"b138114d7116560c","entry":"compute_recency_scores","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_dynamic.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_dynamic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"position_ids:Tensor/2/int, recency_exp:float/0/float, recency_coeff:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"b138114d7116560c"}},{"code_sha256":"aa010c2bd0aa74b0","code_sha256_prefix":"aa010c2bd0aa74b0","entry":"convert_to_tensor","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/deep_embedding.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/deep_embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"el:list/1/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"aa010c2bd0aa74b0"},"code_page":"/code/convert-to-tensor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"aa010c2bd0aa74b0"}},{"code_sha256":"a6c6ee847acad66b","code_sha256_prefix":"a6c6ee847acad66b","entry":"get_cma_defaults","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_evolution/cma_es.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_evolution/cma_es.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pop_size:int/0/int, elite_pop_size:int/0/int, param_size:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"a6c6ee847acad66b"}},{"code_sha256":"36754005e03e2458","code_sha256_prefix":"36754005e03e2458","entry":"get_property_list_from_elements","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_deep_components.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_deep_components.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"property:str/0/str, elements:list/1/Element","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"36754005e03e2458"}},{"code_sha256":"82650da99214bdf2","code_sha256_prefix":"82650da99214bdf2","entry":"reduce_stats","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/deep.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/deep.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"list_of_lists:list/1/list, stat_name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"82650da99214bdf2"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"82650da99214bdf2"}},{"code_sha256":"941a06561780b35a","code_sha256_prefix":"941a06561780b35a","entry":"stat_fn_list","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/deep.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/deep.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"list_of_lists:list/1/list, index:NoneType/0/?, stats_to_return:list/1/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"941a06561780b35a"}},{"code_sha256":"ed9673e65d4694aa","code_sha256_prefix":"ed9673e65d4694aa","entry":"stat_fn_tensor","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/deep.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/deep.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input_tensor:Tensor/2/float, index:NoneType/0/?, stats_to_return:list/1/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"ed9673e65d4694aa"}},{"code_sha256":"5033508c5b925cb2","code_sha256_prefix":"5033508c5b925cb2","entry":"threshold_score_idxs","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_dynamic.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_dynamic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"masked_full_scores:Tensor/2/float, dynamic_thresh:float/0/float, preserve_order:bool/0/bool, cache_size:NoneType/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"5033508c5b925cb2"}},{"code_sha256":"998a8e8e5f062104","code_sha256_prefix":"998a8e8e5f062104","entry":"true_for_all","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_deep_components.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_deep_components.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"property:str/0/str, elements:list/1/Element","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"998a8e8e5f062104"}},{"code_sha256":"62e579d3352bdb8e","code_sha256_prefix":"62e579d3352bdb8e","entry":"true_for_any","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_policy/base_deep_components.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_policy/base_deep_components.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"property:str/0/str, elements:list/1/Element","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"62e579d3352bdb8e"}},{"code_sha256":"0c0fa69e90becc08","code_sha256_prefix":"0c0fa69e90becc08","entry":"full_eigen_decomp","repo":"SakanaAI/evo-memory","repo_kind":"official","path":"memory_evolution/cma_es.py","file_url":"https://github.com/SakanaAI/evo-memory/blob/HEAD/memory_evolution/cma_es.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SakanaAI/evo-memory when it was checked","mcp_get_code":{"code_sha256":"0c0fa69e90becc08"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"22027b731afaa2b53007d0baed77771c50329ec0ea22212ca6976ce1132cda0e","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}