{"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/sequence-modeling-with-multiresolution","title":"Sequence Modeling with Multiresolution Convolutional Memory","arxiv_id":"2305.01638","date":"2023-05-02","proceeding":null,"authors":["Jiaxin Shi","Ke Alexander Wang","Emily B. Fox"],"abstract":"Efficiently capturing the long-range patterns in sequential data sources salient to a given task -- such as classification and generative modeling -- poses a fundamental challenge. Popular approaches in the space tradeoff between the memory burden of brute-force enumeration and comparison, as in transformers, the computational burden of complicated sequential dependencies, as in recurrent neural networks, or the parameter burden of convolutional networks with many or large filters. We instead take inspiration from wavelet-based multiresolution analysis to define a new building block for sequence modeling, which we call a MultiresLayer. The key component of our model is the multiresolution convolution, capturing multiscale trends in the input sequence. Our MultiresConv can be implemented with shared filters across a dilated causal convolution tree. Thus it garners the computational advantages of convolutional networks and the principled theoretical motivation of wavelet decompositions. Our MultiresLayer is straightforward to implement, requires significantly fewer parameters, and maintains at most a $\\mathcal{O}(N\\log N)$ memory footprint for a length $N$ sequence. Yet, by stacking such layers, our model yields state-of-the-art performance on a number of sequence classification and autoregressive density estimation tasks using CIFAR-10, ListOps, and PTB-XL datasets.","url_abs":"https://arxiv.org/abs/2305.01638v2","url_pdf":"https://arxiv.org/pdf/2305.01638v2.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":"sequence-modeling-with-multiresolution","repo_url":"https://github.com/thjashin/multires-conv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"listops","task_name":"ListOps"},{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"}],"methods":[{"method_slug":"causal-convolution","method_name":"Causal Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-image-classification-on-sequential-1","task":"Sequential Image Classification","dataset":"Sequential CIFAR-10","model":"MultiresConv","rank_in_archive_order":1,"of":13,"metrics":{"Unpermuted Accuracy":"93.15%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.01638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01638"}},"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":"deterministic:regex_extraction","url":"https://github.com/thjashin/multires-conv","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"c27418dba9fbd66d","entry":"MultiresLayer","repo":"thjashin/multires-conv","repo_kind":"official","path":"layers/multireslayer.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/layers/multireslayer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c27418dba9fbd66d"}},{"code_sha256_prefix":"88f02c31c56c7058","entry":"forward_uniform","repo":"thjashin/multires-conv","repo_kind":"official","path":"layers/multireslayer.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/layers/multireslayer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88f02c31c56c7058"}},{"code_sha256_prefix":"d34b5691b224ae80","entry":"masked_meanpool","repo":"thjashin/multires-conv","repo_kind":"official","path":"classification.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/classification.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d34b5691b224ae80"}},{"code_sha256_prefix":"32d5fef9113aac56","entry":"eval","repo":"thjashin/multires-conv","repo_kind":"official","path":"autoregressive.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32d5fef9113aac56"}},{"code_sha256_prefix":"a50200f714b086df","entry":"forward_fading","repo":"thjashin/multires-conv","repo_kind":"official","path":"layers/multireslayer.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/layers/multireslayer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a50200f714b086df"}},{"code_sha256_prefix":"6bde61fec84781de","entry":"train","repo":"thjashin/multires-conv","repo_kind":"official","path":"classification.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/classification.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bde61fec84781de"}},{"code_sha256_prefix":"ad628a83df7e160a","entry":"train","repo":"thjashin/multires-conv","repo_kind":"official","path":"autoregressive.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad628a83df7e160a"}},{"code_sha256_prefix":"b05c3cd049bf812e","entry":"uniform_tree_select","repo":"thjashin/multires-conv","repo_kind":"official","path":"layers/multireslayer.py","file_url":"https://github.com/thjashin/multires-conv/blob/HEAD/layers/multireslayer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b05c3cd049bf812e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}