English(EN) Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization

新的CoverPruner方法优化了视觉语言模型中的视觉标记修剪

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 04:00

研究人员推出了一种新颖的视觉标记修剪优化方法CoverPruner，用于视觉语言模型（VLMs）。与现有关注选择要保留的标记的方法不同，CoverPruner解决了确保剩余标记充分代表被移除标记的互补问题。通过将修剪表述为表征覆盖最大化（RCM），CoverPruner旨在用查询加权的（query-weighted）需求覆盖全部投影的视觉标记集。该方法在各种VLM架构和压缩率下，尤其是在激进压缩场景下，都展现出了卓越的准确性。 AI

影响通过优化标记修剪来提高视觉语言模型的效率。

排序理由该集群包含一篇研究论文，详细介绍了优化视觉语言模型中视觉标记修剪的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了优化视觉语言模型中视觉标记修剪的新方法。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Qingchan Zhu, Weihang You, Hanqi Jiang, Changdi Yang, Tianming Liu, Geng Yuan · 2026-09-04 04:00

谁代表被修剪者？视觉令牌修剪作为覆盖优化

arXiv:2609.03158v1 Announce Type: cross Abstract: Visual token pruning reduces the inference cost of vision-language models (VLMs), but most methods only ask which tokens to keep. This retained-token view can keep redundant high-scoring tokens while leaving discarded evidence wit…

本文如何被排名

报道来源 [1]

谁代表被修剪者？视觉令牌修剪作为覆盖优化

相关实体

相关话题