PulseAugur
实时 18:36:02

新的GSTEP框架修剪VideoLLM的token以提高效率

研究人员开发了GSTEP,一个旨在提高视频大型语言模型(VideoLLMs)效率的新型修剪框架。与先前在片段内局部修剪token的方法不同,GSTEP将视频建模为连续的时空信息流。它通过结合时空信息来计算token级别的密度,从而实现全局token采样,平衡信息密度和覆盖范围。实验表明,GSTEP可以在保持高性能的同时修剪大部分视觉token,从而在不同模型和设置下改善准确性-效率的权衡。 AI

影响 该方法可以显著降低运行VideoLLMs的计算成本,使其在需要实时视频理解的应用中更易于访问。

排序理由 详细介绍一种提高VideoLLM效率的新方法的学术论文。[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 →

新的GSTEP框架修剪VideoLLM的token以提高效率

本文如何被排名

Signal score
0 / 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VideoLLM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
30 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Mengjie Zhang, Qihui Zhu, Tao Zhang, Shuangwu Chen, Huihuang Qin, Yu Guo, Shenghao Ye, Zijian Wen, Yunpeng Hou, Dong Jin, Xiaobin Tan, Huasen He, Jian Yang ·

    GSTEP:面向高效视频大语言模型的全局时空密度驱动视觉令牌剪枝

    arXiv:2608.03083v1 Announce Type: cross Abstract: Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number of redundant spatio-temporal visual tokens in long videos. Existing token prunin…