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.
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...
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...
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.
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.
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...
arXiv:2604. 22901v2 Announce Type: replace Abstract: Diffusion models achieve remarkable success in time series generation.
Interactive video world models need to generate each video chunk efficiently while responding faithfully to user controls. Many systems use chunk-wise autoregressive generation with few-step denoising...
arXiv:2606. 26778v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs.
arXiv:2610.08777v1 Announce Type: new Abstract: Interactive video world models need to generate each video chunk efficiently while responding faithfully to user controls. Many systems use chunk-wise...
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introdu...
Pixel‑Space Diffusion via Observation Operators introduces a new framework for pixel‑space diffusion models that addresses a scale‑time mismatch in existing methods. By replacing fixed full‑image supervision with a time‑indexed observation trajectory that progresses from coarse structures to the full image, the model aligns supervision with the natural recovery order of image details. The approach employs Gaussian‑Lanczos operators and a GL‑CoDA decoder to refine features progressively, resulting in faster convergence and higher generation quality, achieving an FID of 1.52 on ImageNet‑256.
CacheScope is a training‑free method that accelerates diffusion transformer inference by selectively replacing full denoising steps with cached approximations. It identifies high‑risk reuse steps online by normalizing probe‑output variation with input displacement, allowing the system to fall back to exact computation only when necessary. The approach achieves up to 3.57× speed‑up and reduces median LPIPS by up to 70.1% on several state‑of‑the‑art models without requiring additional training or offline scheduling.