mlsanityData to 7 Oct 2026

MambaSL: Exploring Single-Layer Mamba for Time Series Classification

arXiv 2604.15174 ↗First posted 16 Apr 2026cs.LG cs.AIcited by 3

On the map: State-space sequence models (S4, Mamba) → Time series forecasting with SSMs

Abstract (arXiv)

Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classification (TSC) has remained limited. We propose MambaSL, a framework that minimally redesigns the selective SSM and projection layers of a single-layer Mamba, guided by four TSC-specific hypotheses. To address benchmarking limitations -- restricted configurations, partial University of East Anglia (UEA) dataset coverage, and insufficiently reproducible setups -- we re-evaluate 20 strong baselines across all 30 UEA datasets under a unified protocol. As a result, MambaSL achieves state-of-the-art performance with statistically significant average improvements, while ensuring reproducibility via public checkpoints for all evaluated models. Together with visualizations, these results demonstrate the potential of Mamba-based architectures as a TSC backbone.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Time series forecasting with SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 43 of its 57 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

43 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification6 Jun
  2. 2024Is Mamba Effective for Time Series Forecasting?17 Mar
  3. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting14 Mar

Other references · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  10. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  11. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  12. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
28 more
  1. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  2. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  3. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  4. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  5. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  6. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  7. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  8. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  9. 2018The UEA multivariate time series classification archive, 2018cited by 330
  10. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  11. 2022Long Range Language Modeling via Gated State Spacescited by 265
  12. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  13. 2022Transformer Quality in Linear Timecited by 189
  14. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  15. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 158
  16. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 146
  17. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  18. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  19. 2021MultiRocket: Multiple pooling operators and transformations for fast and effective time series classificationcited by 89
  20. 2024TSLANet: Rethinking Transformers for Time Series Representation Learningcited by 71
  21. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
  22. 2024Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classificationcited by 53
  23. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52
  24. 2020The Canonical Interval Forest (CIF) Classifier for Time Series Classificationcited by 48
  25. 2024aeon: a Python toolkit for learning from time seriescited by 46
  26. 2024TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysiscited by 37
  27. 2017Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognitioncited by 19
  28. 2023Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fieldscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrencecited by 0
  2. 2026When Labels Are Scarce: An Oscillatory State Space Model for Vibration Diagnosiscited by 0
  3. 2026MASCIT: A Mask-Aware State Space Classifier for Naturally Irregular Time Seriescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Simple State Space Model Excels at Multivariate Time Series Classification
  2. 2024Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data
  3. 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
  4. 2024FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting
  5. 2026A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models
  6. 2024A Mamba Foundation Model for Time Series Forecasting
  7. 2025Block-Biased Mamba for Long-Range Sequence Processing
  8. 2024SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting