arXiv Computer Vision October 5, 2026 By Zhendong Mi, Pu Zhao, Ziyu Hu, Xiaodong Yu, Yanzhi Wang, Grace Li Zhang, Shaoyi Huang

SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching

Read the original on arXiv Computer Vision →

SpectralCache is a training‑free framework that accelerates diffusion‑based world models by exploiting the stability of singular subspaces and predictable evolution of singular values across denoising steps. It reuses these stable subspaces and estimates low‑dimensional singular values via linear extrapolation, while also skipping expensive backbone evaluations through singular value scaling. Experiments on models such as HunyuanWorld‑Voyager‑13B show a 5.22× speed‑up with no loss in generation quality, outperforming existing caching methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Oct 1

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

arXiv:2603.01623v2 Announce Type: replace Abstract: Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference spe...

By Jiaqi Han, Juntong Shi, Puheng Li, Haotian Ye, Qiushan Guo, Stefano Ermon

llms diffusion efficiency benchmarks

arXiv Machine Learning

Sep 22

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

arXiv:2602.24208v2 Announce Type: replace-cross Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequenti...

By Yasaman Haghighi, Alexandre Alahi

diffusion benchmarks

Hugging Face Trending Papers

Jul 26

OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models

High-resolution image and video diffusion models, including SD3, FLUX, and recent video diffusion transformers, have substantially improved generative quality but remain expensive at inference time because they repeatedly evaluate attention-heavy denoisers over many sampling steps. We address this inefficiency by exploiting redundancy in intermediate diffusion features rather than changing model weights or retraining.

llms diffusion efficiency

arXiv Machine Learning

Jul 31

FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference

arXiv:2607. 27842v1 Announce Type: cross Abstract: Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive.

By Hanshuai Cui, Zhiqing Tang, Zhi Yao, Qianli Ma, Fanshuai Meng, Weijia Jia

diffusion

Hugging Face Trending Papers

Aug 18

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature c...

diffusion

arXiv Machine Learning

Jul 28

Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

arXiv:2604. 22901v2 Announce Type: replace Abstract: Diffusion models achieve remarkable success in time series generation.

By Dong Liu, Yanxuan Yu, Ying Nian Wu

llms diffusion

One email a morning, machine-written

Related stories

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models

FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching