mlsanityData to 7 Oct 2026

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

arXiv 2403.13802 ↗First posted 20 Mar 2024cs.CV cs.AI cs.CLcited by 84

On the map: Diffusion models → Medical imaging and segmentation

also in 1 more
Abstract (arXiv)

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called Mamba to extend its applicability to visual data generation. Firstly, we identify a critical oversight in most current Mamba-based vision methods, namely the lack of consideration for spatial continuity in the scan scheme of Mamba. Secondly, building upon this insight, we introduce a simple, plug-and-play, zero-parameter method named Zigzag Mamba, which outperforms Mamba-based baselines and demonstrates improved speed and memory utilization compared to transformer-based baselines. Lastly, we integrate Zigzag Mamba with the Stochastic Interpolant framework to investigate the scalability of the model on large-resolution visual datasets, such as FacesHQ 1024× 1024 and UCF101, MultiModal-CelebA-HQ, and MS COCO 256× 256 . Code will be released at https://taohu.me/zigma/

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 96 of its 120 references that are in the map. First posted on arXiv 20 Mar 2024.

Builds on

96 of 120 references.

References · 96

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  12. 2022Scalable Diffusion Models with Transformerscited by 5,931
38 more
  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2020Longformer: The Long-Document Transformercited by 3,362
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  12. 2022Video Diffusion Modelscited by 2,280
  13. 2020Reformer: The Efficient Transformercited by 1,658
  14. 2020Rethinking Attention with Performerscited by 1,584
  15. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  16. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  17. 2021Variational Diffusion Modelscited by 1,145
  18. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  19. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  20. 2024VMamba: Visual State Space Modelcited by 955
  21. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  22. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  23. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  24. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  25. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  26. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  27. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  28. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 495
  29. 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 490
  30. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  31. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 418
  32. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 412
  33. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  34. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  35. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  36. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 286
  37. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  38. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 233

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 25; 2025: 39; 2026: 20.

84 papers.

Sort:

By area:

  1. 2024Demystify Mamba in Vision: A Linear Attention Perspectivecited by 101
  2. 2024Scaling Diffusion Transformers to 16 Billion Parameterscited by 65
  3. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  4. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  5. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  6. 2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 43
  7. 2024LinFusion: 1 GPU, 1 Minute, 16K Imagecited by 42
  8. 2024A Survey of Mambacited by 39
  9. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 39
  10. 2025FlexVAR: Flexible Visual Autoregressive Modeling without Residual Predictioncited by 22
  11. 2024Autoregressive Pretraining with Mamba in Visioncited by 21
  12. 2025TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Trainingcited by 21
38 more
  1. 2024SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoisingcited by 20
  2. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  3. 2025MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generationcited by 12
  4. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generationcited by 11
  5. 2024[MASK] is All You Needcited by 11
  6. 2025OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Modelscited by 11
  7. 2025M4V: Multimodal Mamba for Efficient Text-to-Video Generationcited by 11
  8. 2025LiT: Delving into a Simple Linear Diffusion Transformer for Image Generationcited by 9
  9. 2025Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigationcited by 9
  10. 2025EDiT: Efficient Diffusion Transformers with Linear Compressed Attentioncited by 7
  11. 2024Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancementcited by 6
  12. 2025TransMamba: Fast Universal Architecture Adaption from Transformers to Mambacited by 6
  13. 2025VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesiscited by 6
  14. 2025MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recoverycited by 6
  15. 2024Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingcited by 5
  16. 2025OuroMamba: A Data-Free Quantization Framework for Vision Mambacited by 5
  17. 2025SaMam: Style-aware State Space Model for Arbitrary Image Style Transfercited by 5
  18. 2025ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Modelscited by 5
  19. 2025U-Shape Mamba: State Space Model for faster diffusioncited by 5
  20. 2024MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Modelcited by 4
  21. 2024Scaling Image Tokenizers with Grouped Spherical Quantizationcited by 4
  22. 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Spacecited by 4
  23. 2025FlexiD-Fuse: Flexible number of inputs multi-modal medical image fusion based on diffusion modelcited by 4
  24. 2025DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbonecited by 4
  25. 2024GG-SSMs: Graph-Generating State Space Modelscited by 3
  26. 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipationcited by 3
  27. 2025MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentationcited by 3
  28. 2025RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restorationcited by 3
  29. 2025End-to-End Multi-Modal Diffusion Mambacited by 3
  30. 2026StyMam: A Mamba-Based Generator for Artistic Style Transfercited by 3
  31. 2026Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformerscited by 3
  32. 2024MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mambacited by 2
  33. 2025MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimationcited by 2
  34. 2025RiverMamba: A State Space Model for Global River Discharge and Flood Forecastingcited by 2
  35. 2025EgoMusic-driven Human Dance Motion Estimation with Skeleton Mambacited by 2
  36. 2025Learning Human Motion with Temporally Conditional Mambacited by 2
  37. 2025Schr"odinger Bridge Mamba for One-Step Speech Enhancementcited by 2
  38. 2025DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modelingcited by 2

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Visual Mamba: A Survey and New Outlooks
  2. 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
  3. 2026Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
  4. 2024Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation
  5. 2024LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba
  6. 2024A Survey on Visual Mamba
  7. 2024Scalable Autoregressive Image Generation with Mamba
  8. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series