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:2608. 01740v1 Announce Type: new Abstract: Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps.
Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps. Recent work has mainly focused on designing stronger forecasters.
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...
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.
The paper introduces TRACK, a training‑free trajectory routing method that accelerates video diffusion by selectively switching between large and small models during denoising steps. A calibration process generates a disagreement score map, guiding the selection of the appropriate model at each step to maintain quality while reducing computational cost. Experiments on Wan 2.1, Cosmos 3, TurboDiffusion, and FastVideo show speedups ranging from 1.95× to 2.73× with comparable quality and diversity.
Accelerating Video Diffusion via Training-Free Trajectory Routing (TRACK) introduces a heterogeneous denoising strategy that switches between large and small diffusion models at selected steps, determined by a calibration process that measures disagreement between model predictions. By routing quality-sensitive steps to the large model and low-disagreement steps to the small model, TRACK achieves significant speedups—up to 2.73×—across several video diffusion benchmarks while maintaining comparable quality and diversity. The method requires no retraining, architectural changes, or online dual-model evaluation, making it a practical acceleration paradigm for video diffusion.
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:2603. 14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility?
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
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...