English(EN) Adaptive Visual Token Reduction for Accelerated Image Understanding

新的ReFIT框架通过自适应标记缩减加速视觉语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-08 04:00

研究人员开发了ReFIT，一个新颖的框架，旨在提高大型视觉语言模型在处理高分辨率图像时的效率。ReFIT采用指令引导的视觉标记缩减，利用相关性引导窗口重塑（RWR）来识别和适应与指令相关的区域，并通过指令引导标记精炼（ITR）来消除多余的标记。这种方法旨在保留空间结构信息，例如通常在更简单的标记缩减方法中会丢失的长文本。在各种视觉问答基准上的实验表明，ReFIT在提高准确性的同时降低了计算需求。 AI

影响这种新方法可以显著降低运行大型视觉语言模型的计算成本，使其在各种应用中更易于访问和更高效。

排序理由详细介绍一种提高AI模型效率的新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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; 详细介绍一种提高AI模型效率的新方法的学术论文。[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。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Seyoung Jeong, Jong Pil Yun, Sang Jun Lee · 2026-10-08 04:00

自适应视觉标记缩减以加速图像理解

arXiv:2610.09252v1 Announce Type: new Abstract: Large Vision-Language Models achieve strong VQA performance, but processing high-resolution, information-rich images requires substantial computation, motivating visual token reduction. However, existing methods often prune individu…

本文如何被排名

报道来源 [1]

自适应视觉标记缩减以加速图像理解

相关实体

相关话题