English(EN) Training-Free Predictive Spatio-Temporal Token Pruning for Few-Step Autoregressive Video Diffusion

新框架PreSTP加速视频扩散模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了PreSTP，一个新颖的无训练框架，旨在加速自回归视频扩散模型。该方法基于跨帧相似性和去噪过程中的早期收敛来识别和剪枝冗余令牌。PreSTP在较短视频生成中实现了1.52倍至3.20倍的显著加速，在较长序列中最高可达1.96倍，同时还改善了效率-保真度权衡并缓解了长时程漂移。 AI

影响加速视频生成效率，可能实现实时应用并改善长篇内容创作。

排序理由这是一篇详细介绍视频扩散模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍视频扩散模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Jia Li, Xurui Peng, Xing Wang, Hayden Kwok-Hay So · 2026-11-06 05:00

无训练的预测时空令牌剪枝用于少样本自回归视频扩散

arXiv:2611.07551v1 Announce Type: new Abstract: Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further accelerating these models toward real-time generation remains challenging, as fe…