Papers › xLSTM: Extended Long Short-Term Memory

xLSTM: Extended Long Short-Term Memory

7 May 2024arXiv:2405.04517archive 2025-07-28

Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter

In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in particular they constituted the first Large Language Models (LLMs). However, the advent of the Transformer technology with parallelizable self-attention at its core marked the dawn of a new era, outpacing LSTMs at scale. We now raise a simple question: How far do we get in language modeling when scaling LSTMs to billions of parameters, leveraging the latest techniques from modern LLMs, but mitigating known limitations of LSTMs? Firstly, we introduce exponential gating with appropriate normalization and stabilization techniques. Secondly, we modify the LSTM memory structure, obtaining: (i) sLSTM with a scalar memory, a scalar update, and new memory mixing, (ii) mLSTM that is fully parallelizable with a matrix memory and a covariance update rule. Integrating these LSTM extensions into residual block backbones yields xLSTM blocks that are then residually stacked into xLSTM architectures. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.

PaperPDFCodeCode Syntology ran

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

No sample from the archive's official repository (nx-ai/xlstm) is linked to this paper; the 9 samples below come from 1 community repository. Syntology harvested code from nx-ai/xlstm for another paper.

nx-ai/xlstm: Syntology's graph links these samples to xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference (arXiv:2503.13427; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 9 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 9 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nx-ai/xlstm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference (arXiv:2503.13427; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
gonzalopezgil/xlstm-ts mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
nx-ai/mlstm_kernels mentioned on GitHubjaxNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity (arXiv:2510.02228; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
nx-ai/xlstm-jax mentioned on GitHubjaxNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity (arXiv:2510.02228; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
smvorwerk/xlstm-cuda mentioned on GitHubpytorchSyntology: not harvested 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

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

7ran
2unverified

Licence: 0 of the 9 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 gonzalopezgil/xlstm-ts. “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.

gonzalopezgil/xlstm-ts community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
create_dataloader in 35 papers src/ml/models/xlstm_ts/training.py ran MIT (permissive) · c418ccbf439fb6c1 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, batch_size:int/0/int, shuffle:bool/0/bool · returned DataLoader · level recorded 2026-09-24
display_metrics src/ml/results/results.py ran MIT (permissive) · 6ecfef88bb7757dc · report fixture: signature metrics_accumulator:dict/0/?, metrics_accumulator_denoised:dict/0/? · returned DataFrame · level recorded 2026-09-24
get_logger in 383 papers src/ml/utils/logger.py ran MIT (permissive) · 5a707ddedc88e249 · report fixture: signature name:str/0/str, log_to_file:bool/0/bool, file_path:str/0/str · returned Logger · level recorded 2026-09-24
inverse_normalise_data_xlstm src/ml/models/xlstm_ts/preprocessing.py ran MIT (permissive) · 41d97ba1265b3c73 · report fixture: signature data:Tensor/2/float, scaler:MinMaxScaler/0/? · returned ndarray · level recorded 2026-09-24
normalise_data_xlstm src/ml/models/xlstm_ts/preprocessing.py ran fingerprinted MIT (permissive) · 24736fff7894ed00 · report fixture: signature data:ndarray/2/float · returned tuple · level recorded 2026-09-25
show_results src/ml/results/results.py ran MIT (permissive) · a32843f8e0256e8a · report fixture: signature results:DataFrame/0/?, data_type:str/0/str · returned DataFrame · level recorded 2026-09-24
validate_date src/gui/utils.py ran MIT (permissive) · dc006911ff24188e · report fixture: signature date_text:str/0/str · returned bool · level recorded 2026-09-24
evaluate_model in 54 papers src/ml/models/xlstm_ts/training.py unverified MIT (permissive) · eefa6a8362a8958c · report
train_model in 103 papers src/ml/models/xlstm_ts/training.py unverified MIT (permissive) · 5fec394cd964815b · report

Tasks

Language ModelingLanguage ModellingState Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEBatch NormalizationConvolutionDense ConnectionsDropoutLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationTransformermLSTM

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