mlsanityData to 14 Oct 2026

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

arXiv 2510.20348 ↗First posted 23 Oct 2025cs.CVcited by 3

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for diffusion models are accumulated over denoising steps in a sampling process. To alleviate the error accumulation problem, AccuQuant minimizes the discrepancies between outputs of a full-precision diffusion model and its quantized version within a couple of denoising steps. That is, it simulates multiple denoising steps of a diffusion sampling process explicitly for quantization, accounting the accumulated errors over multiple denoising steps, which is in contrast to previous approaches to imitating a training process of diffusion models, namely, minimizing the discrepancies independently for each step. We also present an efficient implementation technique for AccuQuant, together with a novel objective, which reduces a memory complexity significantly from O(n) to O(1), where n is the number of denoising steps. We demonstrate the efficacy and efficiency of AccuQuant across various tasks and diffusion models on standard benchmarks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 53 of its 61 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

53 of 61 references.

Closest ancestors · 20

Same direction, newest first

  1. 2024Timestep-Aware Correction for Quantized Diffusion Models4 Jul
  2. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers25 May
  3. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights18 Apr
  4. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  5. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models27 Nov
  6. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing10 Nov
  7. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models5 Oct
  8. 2023Temporal Dynamic Quantization for Diffusion Models4 Jun
  9. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  10. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  11. 2023ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval5 Feb
  12. 2022Scalable Diffusion Models with Transformers19 Dec
8 more
  1. 2022Post-training Quantization on Diffusion Models28 Nov
  2. 2022On Distillation of Guided Diffusion Models6 Oct
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
21 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  2. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  5. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  6. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  7. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  8. 2021Generating Images with Sparse Representationscited by 266
  9. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  10. 2019Quantization Networkscited by 153
  11. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 151
  12. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  13. 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 117
  14. 2021Network Quantization with Element-wise Gradient Scalingcited by 87
  15. 2020Post-Training Piecewise Linear Quantization for Deep Neural Networkscited by 79
  16. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  17. 2023Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidancecited by 43
  18. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  19. 2024Instance-Aware Group Quantization for Vision Transformerscited by 25
  20. 2021Distance-aware Quantizationcited by 19
  21. 2021Post-Training Sparsity-Aware Quantizationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Shift-and-Sum Quantization for Visual Autoregressive Modelscited by 1
  2. 2026PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformerscited by 1
  3. 2026FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Foldingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
  2. 2024QNCD: Quantization Noise Correction for Diffusion Models
  3. 2025D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
  4. 2025Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion
  5. 2024MPQ-Diff: Mixed Precision Quantization for Diffusion Models
  6. 2024DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
  7. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
  8. 2024PQD: Post-training Quantization for Efficient Diffusion Models