SAKURA架构支持手机端私密图像编辑

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了SAKURA，这是一种云边协同架构，旨在为移动设备上的私密图像编辑高效地提供注意力键值（KV）状态。该系统通过使用细粒度的、感知令牌重要性的压缩方法，并根据网络带宽自适应地选择缓存表示，来解决存储大型、可重用KV状态的挑战。SAKURA还包含一个流水线式运行时，可以将缓存传输和重建与设备端执行重叠，从而显著降低延迟和存储需求，同时保持图像质量。 AI

影响该系统可以提高AI驱动的设备端图像编辑应用程序的效率和隐私性。

排序理由研究论文，详细介绍了一种用于高效模型服务的新系统架构。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种用于高效模型服务的新系统架构。[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: infra, product; 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。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shuncheng Jie, Desen Sun, Ri Hong, Yuyang Tian, Hong Zhang, Sihang Liu · 2026-10-23 04:00

SAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones

arXiv:2610.29733v1 Announce Type: cross Abstract: Diffusion transformers are widely used in image-editing services. To preserve both efficiency and privacy, existing systems commonly rely on cloud-device collaboration. Keeping request-specific inference on the device avoids sendi…

本文如何被排名

报道来源 [1]

SAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones

相关实体

相关话题