mlsanityData to 14 Oct 2026

OuroMamba: A Data-Free Quantization Framework for Vision Mamba

arXiv 2503.10959 ↗First posted 13 Mar 2025cs.CV cs.AIcited by 5

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

We present OuroMamba, the first data-free post-training quantization (DFQ) method for vision Mamba-based models (VMMs). We identify two key challenges in enabling DFQ for VMMs, (1) VMM's recurrent state transitions restricts capturing of long-range interactions and leads to semantically weak synthetic data, (2) VMM activations exhibit dynamic outlier variations across time-steps, rendering existing static PTQ techniques ineffective. To address these challenges, OuroMamba presents a two-stage framework: (1) OuroMamba-Gen to generate semantically rich and meaningful synthetic data. It applies contrastive learning on patch level VMM features generated through neighborhood interactions in the latent state space, (2) OuroMamba-Quant to employ mixed-precision quantization with lightweight dynamic outlier detection during inference. In specific, we present a thresholding based outlier channel selection strategy for activations that gets updated every time-step. Extensive experiments across vision and generative tasks show that our data-free OuroMamba surpasses existing data-driven PTQ techniques, achieving state-of-the-art performance across diverse quantization settings. Additionally, we implement efficient GPU kernels to achieve practical latency speedup of up to 2.36x. Code and synthetic dataset are available here: https://github.com/georgia-tech-synergy-lab/ICCV-OuroMamba

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 41 of its 58 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

41 of 58 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization28 Jan
  2. 2024PTQ4VM: Post-Training Quantization for Visual Mamba29 Dec
  3. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbone10 Jul
  4. 2024Demystify Mamba in Vision: A Linear Attention Perspective26 May
  5. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 35

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Mask R-CNNcited by 7,277
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  5. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  6. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  7. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  8. 2024VMamba: Visual State Space Modelcited by 969
  9. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  10. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 273
  11. 2024QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingcited by 208
  12. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
23 more
  1. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 170
  2. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  3. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  4. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 115
  5. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 94
  6. 2024The Hidden Attention of Mamba Modelscited by 91
  7. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  8. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformerscited by 79
  9. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  10. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 56
  11. 2022PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformerscited by 42
  12. 2018An Introduction to Image Synthesis with Generative Adversarial Netscited by 32
  13. 2024Quamba: A Post-Training Quantization Recipe for Selective State Space Modelscited by 28
  14. 2024MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantizationcited by 28
  15. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformerscited by 19
  16. 2024CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTscited by 17
  17. 2024Mamba-PTQ: Outlier Channels in Recurrent Large Language Modelscited by 15
  18. 2024GrootVL: Tree Topology is All You Need in State Space Modelcited by 13
  19. 2021BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratchcited by 11
  20. 2024Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inferencecited by 7
  21. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformerscited by 7
  22. 2022Positive-Negative Equal Contrastive Loss for Semantic Segmentationcited by 5
  23. 2025QMamba: Post-Training Quantization for Vision State Space Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Acceleratorcited by 3
  2. 2025LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modelingcited by 3
  3. 2025Sequential Token Merging: Revisiting Hidden Statescited by 0
  4. 2026ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGAcited by 0
  5. 2026Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Dualitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
  2. 2025ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba
  3. 2026Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
  4. 2024MambaOut: Do We Really Need Mamba for Vision?
  5. 2024Mamba-R: Vision Mamba ALSO Needs Registers
  6. 2026Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
  7. 2025MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation
  8. 2026Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models