# Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

arXiv: https://arxiv.org/abs/2610.16261 · HTML: https://mlsanity.com/paper/2610.16261/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 38)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [FlatQuant: Flatness Matters for LLM Quantization](https://mlsanity.com/paper/2410.09426/) (2024)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [AffineQuant: Affine Transformation Quantization for Large Language Models](https://mlsanity.com/paper/2403.12544/) (2024)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [Post-training 4-bit quantization of convolution networks for rapid-deployment](https://mlsanity.com/paper/1810.05723/) (2018)
- [MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods](https://mlsanity.com/paper/2501.13484/) (2025)

## Abstract (arXiv)

Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantization remains challenging because selective scan, Mamba's input-dependent state-space operator, induces different activation ranges across spatial tokens. Thus, a single layer-wise clipping range poorly matches all tokens. We propose Token-Group Quantization, a hardware-friendly activation PTQ framework that statically approximates a hardware-unfriendly post-scan grouping oracle, where tokens with similar preferred clipping ranges are assigned to the same group. To avoid runtime post-scan grouping in static low-bit inference, a lightweight predictor infers the groups from pre-scan features available before the quantized scan path. During calibration, we form pseudo-labels by clustering post-scan activation descriptors that capture similar rounding--clipping behavior. At inference, the frozen predictor maps pre-scan features to groups and selects entries from offline-calibrated group-wise clipping-bound tables, without runtime statistics collection, dynamic clipping updates, or post-scan group assignment. To address low-bit restoration degradation, we further introduce a Frequency-Preserving Refinement (FPR) objective for clipping-bound calibration. FPR aligns Fourier amplitude and phase between full-precision teacher and quantized student outputs to preserve high-frequency structures. Across PTQ protocols, bit-widths, backbones, and tasks, our method consistently outperforms prior Mamba and SR PTQ baselines, transfers to Transformer SR and Vision Mamba classification, composes with rotation-based quantization, and achieves 2.23x speedup on Jetson Orin Nano over FP16. Code is available here.