{"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/vision-lstm-xlstm-as-generic-vision-backbone","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","arxiv_id":"2406.04303","date":"2024-06-06","proceeding":null,"authors":["Benedikt Alkin","Maximilian Beck","Korbinian Pöppel","Sepp Hochreiter","Johannes Brandstetter"],"abstract":"Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this report, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even blocks go from bottom to top. Experiments show that ViL holds promise to be further deployed as new generic backbone for computer vision architectures.","url_abs":"https://arxiv.org/abs/2406.04303v2","url_pdf":"https://arxiv.org/pdf/2406.04303v2.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":"vision-lstm-xlstm-as-generic-vision-backbone","repo_url":"https://github.com/NX-AI/vision-lstm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vision-lstm-xlstm-as-generic-vision-backbone","repo_url":"https://github.com/BenediktAlkin/vtab1k-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.04303","atlas_url":"https://app.syntology.ai/?focus=2406.04303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04303"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/NX-AI/vision-lstm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BenediktAlkin/vtab1k-pytorch","reach":null}],"summary":{"ran":7,"ran_draft_wrong":4,"ran_fixture":2,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":19,"ran":14,"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":"f8ca69c110b41703","entry":"CausalConv1d","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8ca69c110b41703"}},{"code_sha256_prefix":"5fa540c6a1346171","entry":"DropPath","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5fa540c6a1346171"}},{"code_sha256_prefix":"a796b1f63f3dfbce","entry":"LayerNorm","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a796b1f63f3dfbce"}},{"code_sha256_prefix":"22cd5400a08af55a","entry":"LinearHeadwiseExpand","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22cd5400a08af55a"}},{"code_sha256_prefix":"70db181d80fa624d","entry":"MultiHeadLayerNorm","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"70db181d80fa624d"}},{"code_sha256_prefix":"6b7511b39ecf627e","entry":"VitPatchEmbed","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b7511b39ecf627e"}},{"code_sha256_prefix":"e56c0fd30e56fabf","entry":"VitPosEmbed2d","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e56c0fd30e56fabf"}},{"code_sha256_prefix":"90263a78b0923104","entry":"_ntuple","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90263a78b0923104"}},{"code_sha256_prefix":"705d17e5f5c0489b","entry":"bias_linspace_init_","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"705d17e5f5c0489b"}},{"code_sha256_prefix":"3852783d3c31c6c8","entry":"interpolate_sincos","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3852783d3c31c6c8"}},{"code_sha256_prefix":"124d9b21f82fcec5","entry":"parallel_stabilized_simple","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"124d9b21f82fcec5"}},{"code_sha256_prefix":"83954f29f639db88","entry":"small_init_","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83954f29f639db88"}},{"code_sha256_prefix":"8aecee1d48ec4f1e","entry":"to_ntuple","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8aecee1d48ec4f1e"}},{"code_sha256_prefix":"b5ad18007daa65d1","entry":"wang_init_","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b5ad18007daa65d1"}},{"code_sha256_prefix":"0c409c165a499499","entry":"MatrixLSTMCell","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"0c409c165a499499"}},{"code_sha256_prefix":"83c87d311ea75cbc","entry":"SequenceTraversal","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"83c87d311ea75cbc"}},{"code_sha256_prefix":"a74a2b2b5da0ef34","entry":"ViLBlock","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"a74a2b2b5da0ef34"}},{"code_sha256_prefix":"b9defe989265d1d9","entry":"ViLLayer","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"b9defe989265d1d9"}},{"code_sha256_prefix":"061ae51a3df25f67","entry":"VisionLSTM","repo":"NX-AI/vision-lstm","repo_kind":"official","path":"vision_lstm/vision_lstm.py","file_url":"https://github.com/NX-AI/vision-lstm/blob/HEAD/vision_lstm/vision_lstm.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":"061ae51a3df25f67"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}