mlsanityData to 14 Oct 2026

Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection

arXiv 2511.17634 ↗First posted 19 Nov 2025cs.CVcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper presents a novel framework to accelerate score-based diffusion models. It first converts the standard stable diffusion model into the Fokker-Planck formulation which results in solving large linear systems for each image. For training involving many images, it can lead to a high computational cost. The core innovation is a cross-matrix Krylov projection method that exploits mathematical similarities between matrices, using a shared subspace built from ``seed" matrices to rapidly solve for subsequent ``target" matrices. Our experiments show that this technique achieves a 15.8% to 43.7% time reduction over standard sparse solvers. Additionally, we compare our method against DDPM baselines in denoising tasks, showing a speedup of up to 115×. Furthermore, under a fixed computational budget, our model is able to produce high-quality images while DDPM fails to generate recognizable content, illustrating our approach is a practical method for efficient generation in resource-limited settings.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 13 of its 23 references that are in the map. First posted on arXiv 19 Nov 2025.

Builds on

13 of 23 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Efficient Denoising using Score Embedding in Score-based Diffusion Models10 Apr
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun
  7. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 6

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2020Efficient Learning of Generative Models via Finite-Difference Score Matchingcited by 49
  6. 2022Probability flow solution of the Fokker-Planck equationcited by 47

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PhyloSDF: Phylogenetically-Conditioned Neural Generation of 3D Skull Morphology via Residual Flow Matchingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
  2. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
  3. 2026Improved Distributional Diffusion Models
  4. 2024Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models
  5. 2022Denoising MCMC for Accelerating Diffusion-Based Generative Models
  6. 2026A Random Matrix Theory Perspective on the Consistency of Diffusion Models
  7. 2025Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
  8. 2021Score-based diffusion models for accelerated MRI