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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.04517")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: community (archive-listed): 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nx-ai/xlstm officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
gonzalopezgil/xlstm-ts mentioned on GitHubpytorchMIT report
nx-ai/mlstm_kernels mentioned on GitHubjaxNOASSERTION report
nx-ai/xlstm-jax mentioned on GitHubjaxNOASSERTION report
smvorwerk/xlstm-cuda mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9unverified

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

create_dataloader gonzalopezgil/xlstm-ts/src/ml/models/xlstm_ts/training.py community (archive-listed) unverified MIT (permissive) · c418ccbf439fb6c1 · report
display_metrics gonzalopezgil/xlstm-ts/src/ml/results/results.py community (archive-listed) unverified MIT (permissive) · 6ecfef88bb7757dc · report
evaluate_model gonzalopezgil/xlstm-ts/src/ml/models/xlstm_ts/training.py community (archive-listed) unverified MIT (permissive) · eefa6a8362a8958c · report
get_logger gonzalopezgil/xlstm-ts/src/ml/utils/logger.py community (archive-listed) unverified MIT (permissive) · 5a707ddedc88e249 · report
inverse_normalise_data_xlstm gonzalopezgil/xlstm-ts/src/ml/models/xlstm_ts/preprocessing.py community (archive-listed) unverified MIT (permissive) · 41d97ba1265b3c73 · report
normalise_data_xlstm gonzalopezgil/xlstm-ts/src/ml/models/xlstm_ts/preprocessing.py community (archive-listed) unverified MIT (permissive) · 24736fff7894ed00 · report
show_results gonzalopezgil/xlstm-ts/src/ml/results/results.py community (archive-listed) unverified MIT (permissive) · a32843f8e0256e8a · report
train_model gonzalopezgil/xlstm-ts/src/ml/models/xlstm_ts/training.py community (archive-listed) unverified MIT (permissive) · 5fec394cd964815b · report
validate_date gonzalopezgil/xlstm-ts/src/gui/utils.py community (archive-listed) unverified MIT (permissive) · dc006911ff24188e · 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