{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/associative-recurrent-memory-transformer","title":"Associative Recurrent Memory Transformer","arxiv_id":"2407.04841","date":"2024-07-05","proceeding":null,"authors":["Ivan Rodkin","Yuri Kuratov","Aydar Bulatov","Mikhail Burtsev"],"abstract":"This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is based on transformer self-attention for local context and segment-level recurrence for storage of task specific information distributed over a long context. We demonstrate that ARMT outperfors existing alternatives in associative retrieval tasks and sets a new performance record in the recent BABILong multi-task long-context benchmark by answering single-fact questions over 50 million tokens with an accuracy of 79.9%. The source code for training and evaluation is available on github.","url_abs":"https://arxiv.org/abs/2407.04841v1","url_pdf":"https://arxiv.org/pdf/2407.04841v1.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":"associative-recurrent-memory-transformer","repo_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.04841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04841"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":10},"by_repo_kind":{"official":{"samples":14,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"db8deebff0d5256c","entry":"allocate_mem_buff","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"megatron/memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/megatron/memory.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"db8deebff0d5256c"}},{"code_sha256_prefix":"b6bf9c8a7315bb78","entry":"bias_dropout_add","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"megatron/model/transformer.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/megatron/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6bf9c8a7315bb78"}},{"code_sha256_prefix":"5b2f7f0576ba5c71","entry":"deberta_memory_layers_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder/memory_layers.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder/memory_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b2f7f0576ba5c71"}},{"code_sha256_prefix":"dc55ddfafd78b31b","entry":"get_bias_dropout_add","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"megatron/model/transformer.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/megatron/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc55ddfafd78b31b"}},{"code_sha256_prefix":"55583aac4ec58bf6","entry":"deberta_horizontal_memory_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder/horizontal_memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder/horizontal_memory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55583aac4ec58bf6"}},{"code_sha256_prefix":"79e90a746251736b","entry":"generate_pairs","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"run_finetuning_associative_retrieval.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/run_finetuning_associative_retrieval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79e90a746251736b"}},{"code_sha256_prefix":"8a1aaa5bb993da97","entry":"get_mem_buff","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"megatron/memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/megatron/memory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a1aaa5bb993da97"}},{"code_sha256_prefix":"926c84c930441c95","entry":"horizontal_memory_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder/horizontal_memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder/horizontal_memory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"926c84c930441c95"}},{"code_sha256_prefix":"a4bc8265f86d923d","entry":"horizontal_memory_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder_decoder/horizontal_memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder_decoder/horizontal_memory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4bc8265f86d923d"}},{"code_sha256_prefix":"6ba5053e38b057df","entry":"horizontal_memory_forward_1by1","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder_decoder/horizontal_memory.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder_decoder/horizontal_memory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba5053e38b057df"}},{"code_sha256_prefix":"431671633a1530c3","entry":"memory_layers_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/decoder/memory_layers.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/decoder/memory_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"431671633a1530c3"}},{"code_sha256_prefix":"424d63b2052c4ec0","entry":"memory_layers_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder/memory_layers.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder/memory_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"424d63b2052c4ec0"}},{"code_sha256_prefix":"219e86a9d74b05ec","entry":"memory_layers_forward","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/encoder_decoder/memory_layers.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/encoder_decoder/memory_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"219e86a9d74b05ec"}},{"code_sha256_prefix":"e4fc0dbd771c70e4","entry":"memory_layers_forward_r2r","repo":"RodkinIvan/associative-recurrent-memory-transformer","repo_kind":"official","path":"rmt_utils/decoder/memory_layers.py","file_url":"https://github.com/RodkinIvan/associative-recurrent-memory-transformer/blob/HEAD/rmt_utils/decoder/memory_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4fc0dbd771c70e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}