Papers › Vision-LSTM: xLSTM as Generic Vision Backbone

Vision-LSTM: xLSTM as Generic Vision Backbone

6 Jun 2024arXiv:2406.04303archive 2025-07-28

Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter

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.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 14 ran (8 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

NX-AI/vision-lstm officialmentioned on GitHubpytorchSyntology: 19 samples, 14 ran (6 instrument-failed) · 5 unverified report
BenediktAlkin/vtab1k-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations (arXiv:2402.10093; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and Parameter Efficient Fine-tuning via Explained Variance Adaptation (arXiv:2410.07170; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

19 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
2ran; the contract check could not run
7ran
5unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from NX-AI/vision-lstm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

NX-AI/vision-lstm official repository 19 samples, 14 ran (6 instrument-failed) · 5 unverified
CausalConv1d vision_lstm/vision_lstm.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · f8ca69c110b41703 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
vision_lstm/vision_lstm.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 5fa540c6a1346171 · report fixture: signature x:Tensor/2/float, residual_path:callable/0/?, residual_path_kwargs:dict/0/? · returned Tensor · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
vision_lstm/vision_lstm.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · a796b1f63f3dfbce · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
LinearHeadwiseExpand vision_lstm/vision_lstm.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 22cd5400a08af55a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MultiHeadLayerNorm vision_lstm/vision_lstm.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 70db181d80fa624d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VitPatchEmbed vision_lstm/vision_lstm.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 6b7511b39ecf627e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VitPosEmbed2d vision_lstm/vision_lstm.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · e56c0fd30e56fabf · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_ntuple in 17 papers vision_lstm/vision_lstm.py ran · our draft was wrong Apache-2.0 (permissive) · 90263a78b0923104 · report fixture: signature n:int/0/int · returned function · level recorded 2026-09-22
bias_linspace_init_ vision_lstm/vision_lstm.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 705d17e5f5c0489b · report fixture: signature param:Tensor/1/float, start:float/0/float, end:float/0/float · returned Tensor · level recorded 2026-09-22
interpolate_sincos vision_lstm/vision_lstm.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 3852783d3c31c6c8 · report fixture: signature embed:Tensor/4/float, seqlens:list/1/int, mode:str/0/str · returned Tensor · level recorded 2026-09-22
parallel_stabilized_simple vision_lstm/vision_lstm.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 124d9b21f82fcec5 · report fixture: signature queries:Tensor/4/float, keys:Tensor/4/float, values:Tensor/4/float, igate_preact:Tensor/4/float, fgate_preact:Tensor/4/float, lower_triangular_matrix:Tensor/2/bool, stabilize_rowwise:bool/0/bool, eps:float/0/float · returned Tensor · level recorded 2026-09-22
small_init_ vision_lstm/vision_lstm.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 83954f29f639db88 · report fixture: signature param:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
to_ntuple vision_lstm/vision_lstm.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8aecee1d48ec4f1e · report fixture: signature x:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-22
wang_init_ vision_lstm/vision_lstm.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b5ad18007daa65d1 · report fixture: signature param:Tensor/2/float, dim:int/0/int, num_blocks:int/0/int · returned Tensor · level recorded 2026-09-22
MatrixLSTMCell vision_lstm/vision_lstm.py unverified Apache-2.0 (permissive) · 0c409c165a499499 · report
SequenceTraversal vision_lstm/vision_lstm.py unverified Apache-2.0 (permissive) · 83c87d311ea75cbc · report
ViLBlock vision_lstm/vision_lstm.py unverified Apache-2.0 (permissive) · a74a2b2b5da0ef34 · report
ViLLayer vision_lstm/vision_lstm.py unverified Apache-2.0 (permissive) · b9defe989265d1d9 · report
VisionLSTM vision_lstm/vision_lstm.py unverified Apache-2.0 (permissive) · 061ae51a3df25f67 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Vision-LSTM (graph method: Vision-LSTM). 19 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. VisionLSTM entry · level 0 · unverified · 061ae51a3df25f67
  2. LayerNorm model · level 1 · ran · a796b1f63f3dfbce
  3. SequenceTraversal helper · level 0 · unverified · 83c87d311ea75cbc
  4. ViLBlock model · level 0 · unverified · a74a2b2b5da0ef34
  5. VitPatchEmbed helper · level 1 · ran · 6b7511b39ecf627e
  6. VitPosEmbed2d helper · level 1 · ran · e56c0fd30e56fabf
  7. interpolate_sincos helper · level 1 · ran; the contract check could not run (RAISES) · 3852783d3c31c6c8
  8. to_ntuple helper · level 1 · ran · honoured contract · 8aecee1d48ec4f1e
  9. DropPath helper · level 1 · ran · 5fa540c6a1346171
  10. ViLLayer model · level 0 · unverified · b9defe989265d1d9
  11. _ntuple helper · level 1 · ran · our draft was wrong · 90263a78b0923104
  12. CausalConv1d model · level 1 · ran · f8ca69c110b41703
  13. LinearHeadwiseExpand model · level 1 · ran · 22cd5400a08af55a
  14. MatrixLSTMCell model · level 0 · unverified · 0c409c165a499499
  15. small_init_ helper · level 1 · ran · our draft was wrong · 83954f29f639db88
  16. wang_init_ helper · level 1 · ran · our draft was wrong · b5ad18007daa65d1
  17. MultiHeadLayerNorm model · level 1 · ran · 70db181d80fa624d
  18. bias_linspace_init_ helper · level 1 · ran · our draft was wrong · 705d17e5f5c0489b
  19. parallel_stabilized_simple model · level 1 · ran; the contract check could not run (RAISES) · 124d9b21f82fcec5

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.04303") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections