mlsanityData to 7 Oct 2026

Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

arXiv 2402.05892 ↗First posted 8 Feb 2024cs.CVcited by 84

On the map: State-space sequence models (S4, Mamba) → Core SSM architectures for language

Abstract (arXiv)

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs prohibitive compute and memory complexity that scales quadratically w.r.t. the sequence length. A recent architecture, Mamba, based on state space models has been shown to achieve comparable performance for modeling text sequences, while scaling linearly with the sequence length. In this work, we present Mamba-ND, a generalized design extending the Mamba architecture to arbitrary multi-dimensional data. Our design alternatively unravels the input data across different dimensions following row-major orderings. We provide a systematic comparison of Mamba-ND with several other alternatives, based on prior multi-dimensional extensions such as Bi-directional LSTMs and S4ND. Empirically, we show that Mamba-ND demonstrates performance competitive with the state-of-the-art on a variety of multi-dimensional benchmarks, including ImageNet-1K classification, HMDB-51 action recognition, and ERA5 weather forecasting.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 51 of its 66 references that are in the map. First posted on arXiv 8 Feb 2024.

Builds on

51 of 66 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spaces1 Dec
  2. 2021Efficiently Modeling Long Sequences with Structured State Spaces31 Oct

Other references · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  12. 2017The Kinetics Human Action Video Datasetcited by 1,894
37 more
  1. 2018SlowFast Networks for Video Recognitioncited by 1,862
  2. 2021ViViT: A Video Vision Transformercited by 1,610
  3. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  4. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  5. 2021Video Swin Transformercited by 1,090
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  7. 2024VMamba: Visual State Space Modelcited by 955
  8. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  9. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 823
  10. 2016Pixel Recurrent Neural Networkscited by 814
  11. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  12. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  13. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  14. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  15. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
  16. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 412
  17. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  18. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  19. 2019Axial Attention in Multidimensional Transformerscited by 350
  20. 2023ClimaX: A foundation model for weather and climatecited by 325
  21. 2021Video Transformer Networkcited by 271
  22. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  23. 2022DaViT: Dual Attention Vision Transformerscited by 174
  24. 2022Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecastcited by 164
  25. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
  26. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 106
  27. 2016Spatiotemporal Residual Networks for Video Action Recognitioncited by 91
  28. 2022Learning To Recognize Procedural Activities with Distant Supervisioncited by 85
  29. 2021Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction modelscited by 76
  30. 2018Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Predictioncited by 61
  31. 2016Real-time Action Recognition with Enhanced Motion Vector CNNscited by 51
  32. 2022Efficient Movie Scene Detection using State-Space Transformerscited by 51
  33. 2023ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modelingcited by 46
  34. 2022S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spacescited by 41
  35. 2023Reversible Vision Transformerscited by 33
  36. 20232-D SSM: A General Spatial Layer for Visual Transformerscited by 18
  37. 2022Width is Less Important than Depth in ReLU Neural Networkscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 39; 2025: 31; 2026: 14.

84 papers.

Sort:

By area:

  1. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  2. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 142
  3. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognitioncited by 141
  4. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  5. 2024Demystify Mamba in Vision: A Linear Attention Perspectivecited by 101
  6. 2024The Hidden Attention of Mamba Modelscited by 88
  7. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  8. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  9. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
  10. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  11. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 53
  12. 2024A Survey on Visual Mambacited by 50
38 more
  1. 2025STORM: Token-Efficient Long Video Understanding for Multimodal LLMscited by 46
  2. 2024MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selectioncited by 40
  3. 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methodscited by 26
  4. 2024VideoMamba: Spatio-Temporal Selective State Space Modelcited by 25
  5. 2024Matten: Video Generation with Mamba-Attentioncited by 24
  6. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 21
  7. 2024Autoregressive Pretraining with Mamba in Visioncited by 21
  8. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  9. 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Modelcited by 18
  10. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  11. 2025ViT3: Unlocking Test-Time Training in Visioncited by 15
  12. 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecastingcited by 13
  13. 2024ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attentioncited by 13
  14. 2024GrootVL: Tree Topology is All You Need in State Space Modelcited by 13
  15. 2024MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mambacited by 11
  16. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generationcited by 11
  17. 2025M4V: Multimodal Mamba for Efficient Text-to-Video Generationcited by 11
  18. 2024Snakes and Ladders: Two Steps Up for VideoMambacited by 10
  19. 2024ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2cited by 10
  20. 2025AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understandingcited by 9
  21. 2025MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimationcited by 9
  22. 2024MatMamba: A Matryoshka State Space Modelcited by 6
  23. 2025Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlookcited by 6
  24. 2024Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysiscited by 5
  25. 2024Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognitioncited by 5
  26. 2024Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingcited by 5
  27. 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolutioncited by 5
  28. 2024Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformationcited by 4
  29. 2025Parallel Sequence Modeling via Generalized Spatial Propagation Networkcited by 4
  30. 2024Learning 1D Causal Visual Representation with De-focus Attention Networkscited by 3
  31. 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipationcited by 3
  32. 2025On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approachcited by 3
  33. 2025ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mambacited by 3
  34. 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generationcited by 3
  35. 2026HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNetcited by 3
  36. 2024MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentationcited by 2
  37. 2025MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessmentcited by 2
  38. 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognitioncited by 2

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
  2. 2024A Survey of Mamba
  3. 2024Visual Mamba: A Survey and New Outlooks
  4. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models
  5. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
  6. 2024An Empirical Study of Mamba-based Language Models
  7. 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classification
  8. 2026A Simple State Space Model Excels at Multivariate Time Series Classification