mlsanityData to 14 Oct 2026

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

arXiv 2405.14224 ↗First posted 23 May 2024cs.CVcited by 72

On the map: Diffusion models → Medical imaging and segmentation

also in 1 more
Abstract (arXiv)

Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant challenges when dealing with high-resolution images. In this work, we propose Diffusion Mamba (DiM), which combines the efficiency of Mamba, a sequence model based on State Space Models (SSM), with the expressive power of diffusion models for efficient high-resolution image synthesis. To address the challenge that Mamba cannot generalize to 2D signals, we make several architecture designs including multi-directional scans, learnable padding tokens at the end of each row and column, and lightweight local feature enhancement. Our DiM architecture achieves inference-time efficiency for high-resolution images. In addition, to further improve training efficiency for high-resolution image generation with DiM, we investigate "weak-to-strong" training strategy that pretrains DiM on low-resolution images (256× 256) and then finetune it on high-resolution images (512 × 512). We further explore training-free upsampling strategies to enable the model to generate higher-resolution images (e.g., 1024× 1024 and 1536× 1536) without further fine-tuning. Experiments demonstrate the effectiveness and efficiency of our DiM. The code of our work is available here: urlhttps://github.com/tyshiwo1/DiM-DiffusionMamba/.

Key facts. Cited by 72 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 31 of its 38 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

31 of 38 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  12. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
19 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  2. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  3. 2024VMamba: Visual State Space Modelcited by 969
  4. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  5. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  6. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499
  7. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
  8. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  9. 2016Dynamic Filter Networkscited by 319
  10. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  11. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 255
  12. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  13. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 122
  14. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 108
  15. 2023Diffusion Models Without Attentioncited by 75
  16. 2022Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Modelcited by 58
  17. 2024Scalable Diffusion Models with State Space Backbonecited by 45
  18. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  19. 2024Upsample Guidance: Scale Up Diffusion Models without Trainingcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 28; 2025: 29; 2026: 15.

72 papers.

Sort:

By area:

  1. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  2. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 283
  3. 2025DDT: Decoupled Diffusion Transformercited by 109
  4. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 87
  5. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 87
  6. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  7. 2025PixNerd: Pixel Neural Field Diffusioncited by 82
  8. 2025Long-Context State-Space Video World Modelscited by 64
  9. 2024Dynamic Diffusion Transformercited by 62
  10. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 60
  11. 2024DiG: Scalable and Efficient Diffusion Models with Gated Linear Attentioncited by 56
  12. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
38 more
  1. 2024TinyFusion: Diffusion Transformers Learned Shallowcited by 45
  2. 2024LinFusion: 1 GPU, 1 Minute, 16K Imagecited by 43
  3. 2024LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexitycited by 43
  4. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 41
  5. 2024Autoregressive Models in Vision: A Surveycited by 39
  6. 2024SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentationcited by 31
  7. 2025Taming Teacher Forcing for Masked Autoregressive Video Generationcited by 30
  8. 2024Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Modelscited by 23
  9. 2025TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Trainingcited by 21
  10. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  11. 2024FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Modelcited by 15
  12. 2024MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMscited by 14
  13. 2024REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latentscited by 14
  14. 2024DiC: Rethinking Conv3x3 Designs in Diffusion Modelscited by 14
  15. 2026PixelGen: Improving Pixel Diffusion with Perceptual Supervisioncited by 14
  16. 2025Exploring Diffusion Transformer Designs via Graftingcited by 12
  17. 2024MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoderscited by 10
  18. 2025LiT: Delving into a Simple Linear Diffusion Transformer for Image Generationcited by 10
  19. 2024MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generationcited by 8
  20. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolutioncited by 7
  21. 2025Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generationcited by 7
  22. 2025DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modelingcited by 6
  23. 2025DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbonecited by 6
  24. 2025ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Modelscited by 5
  25. 2024LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mambacited by 4
  26. 2024Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformationcited by 4
  27. 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognitioncited by 4
  28. 2025Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generationcited by 3
  29. 2025End-to-End Multi-Modal Diffusion Mambacited by 3
  30. 2026Adaptive 1D Video Diffusion Autoencodercited by 3
  31. 2026Linearizing Vision Transformer with Test-Time Trainingcited by 3
  32. 2024MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mambacited by 2
  33. 2024Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognitioncited by 2
  34. 2025Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshescited by 2
  35. 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognitioncited by 2
  36. 2025Learning Human Motion with Temporally Conditional Mambacited by 2
  37. 2026MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Modelcited by 2
  38. 2026The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latentscited by 2

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation
  2. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation
  3. 2024Dimba: Transformer-Mamba Diffusion Models
  4. 2025U-Shape Mamba: State Space Model for faster diffusion
  5. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Model
  6. 2024Efficient 3D Shape Generation via Diffusion Mamba with Bidirectional SSMs
  7. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  8. 2023Matryoshka Diffusion Models