mlsanityData to 7 Oct 2026

Vision Mamba backbones

212 papers1 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: mamba, vision, visual, state, performance

Key facts. Vision Mamba backbones: 212 papers on arXiv since 2024 (data through 7 Oct 2026). 109 of its 212 mapped papers (51%) cite “Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model” (2024, arXiv 2401.09417). 56 of its 212 mapped papers (26%) cite “LocalMamba: Visual State Space Model with Windowed Selective Scan” (2024, arXiv 2403.09338). 4 new papers 18 Sep–7 Oct.

What’s new

18 Sep – 7 Oct 2026

  1. This week · 1
  2. FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
  3. Earlier · 3
  4. RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision also fits: Video, motion and generative Mamba models
  5. CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention also fits: Point clouds, detection and remote sensing
  6. LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba

Foundations

Most cited by papers here

  1. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model2024cited by 109 here
  2. LocalMamba: Visual State Space Model with Windowed Selective Scan2024cited by 56 here
  3. EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba2024cited by 41 here
  4. PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition2024cited by 41 here
  5. MambaVision: A Hybrid Mamba-Transformer Vision Backbone2024cited by 35 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 98 here
  2. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 20 here
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 146 here
  4. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 34 here
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 109 here
  6. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 26 here
  7. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 25 here
  8. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 41 here
  9. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognitioncited by 41 here
  10. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 21 here
14 more it builds on, not in this chain
  1. 2022Simplified State Space Layers for Sequence Modelingcited by 52 here
  2. 2023Selective Structured State-Spaces for Long-Form Video Understandingcited by 14 here
  3. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 18 here
  4. 2024Mamba-ND: Selective State Space Modeling for Multi-Dimensional Datacited by 16 here
  5. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 20 here
  6. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 31 here
  7. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 37 here
  8. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 56 here
  9. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 17 here
  10. 2024VL-Mamba: Exploring State Space Models for Multimodal Learningcited by 19 here
  11. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inferencecited by 14 here
  12. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 14 here
  13. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 36 here
  14. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 35 here

The 24 most cited of 288.

Browse

30 of 212, ranked 6–35

  1. 6MambaOut: Do We Really Need Mamba for Vision?202421
  2. 7VL-Mamba: Exploring State Space Models for Multimodal Learning202419
  3. 8Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference202414
  4. 9SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series202414
  5. 10Demystify Mamba in Vision: A Linear Attention Perspective202414
  6. 11Mamba-R: Vision Mamba ALSO Needs Registers202413
  7. 12ReMamber: Referring Image Segmentation with Mamba Twister202410
  8. 13Pan-Mamba: Effective pan-sharpening with State Space Model20249
  9. 14A Survey on Visual Mamba20249
  10. 15Autoregressive Pretraining with Mamba in Vision20249
All 30
  1. 16Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation20248
  2. 17VSSD: Vision Mamba with Non-Causal State Space Duality20247
  3. 18DefMamba: Deformable Visual State Space Model20256
  4. 19Vision Mamba: A Comprehensive Survey and Taxonomy20246
  5. 20Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion20246
  6. 21Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning20245
  7. 22RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining20245
  8. 232DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification20245
  9. 24Visual Mamba: A Survey and New Outlooks20244
  10. 25DVMSR: Distillated Vision Mamba for Efficient Super-Resolution20244
  11. 26MambaVC: Learned Visual Compression with Selective State Spaces20244
  12. 27GroupMamba: Efficient Group-Based Visual State Space Model20244
  13. 28Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution20244
  14. 29PTQ4VM: Post-Training Quantization for Visual Mamba20244
  15. 30A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion20243
  16. 31Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain20243
  17. 32MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders20243
  18. 33Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency20243
  19. 34MobileMamba: Lightweight Multi-Receptive Visual Mamba Network20243
  20. 35Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization20252