PulseAugur
中
实时 10:27:10
English(EN) GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs

GeoGR框架通过令牌压缩和路由提升3D VLM效率

研究人员开发了GeoGR,一个旨在提高3D视觉语言模型(VLMs)效率的新型框架。GeoGR采用两阶段方法:GeoSemZip通过整合冗余观测和优先考虑语义显著性来压缩多视图3D场景表示,而GroupRoute通过允许低相关性令牌跳过层并稍后重新加入来优化LLM计算。该方法显著加速了LLM预填充速度,在LLaVA-OneVision-7B和Video-3D LLM-7B等基准测试中,性能保持了原始模型的95%以上,速度提升高达6.8倍。 AI

影响 提高了3D视觉语言模型的效率,可能实现更复杂的场景理解和交互。

排序理由 该条目是arXiv预印本,详细介绍了用于改进3D VLM的新技术框架。[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 →

GeoGR框架通过令牌压缩和路由提升3D VLM效率

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
该条目是arXiv预印本,详细介绍了用于改进3D VLM的新技术框架。[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]

  1. arXiv cs.AI TIER_1 English(EN) · Yongxin Zheng, Hao Wu, Fang Li, Hu Fu, Peiran Yin, Xudong Wang, Haozhe Hu, Xinghao Chen, Yunpu Ma, Wei Zhang, Xiaoyu Shen ·

    GeoGR:用于高效3D VLM的空间-语义令牌压缩与分组路由

    arXiv:2610.13035v1 Announce Type: cross Abstract: Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly. Redundancy arises both from repeated observations of the sam…