{"ID":2839420,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17634","arxiv_id":"2511.17634","title":"Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection","abstract":"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$\\times$. 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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.17634","url_pdf":"https://arxiv.org/pdf/2511.17634v1","authors":"[\"Kaikwan Lau\",\"Andrew S. Na\",\"Justin W. L. Wan\"]","published":"2025-11-19T07:21:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}