PulseAugur
实时 09:59:03
English(EN) CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

新的CoVeR方法为视觉语言模型(VLM)中的三维推理剪枝视觉令牌

研究人员开发了CoVeR,一种在处理由多视角图像表示的三维场景时,用于剪枝视觉语言模型(VLM)中视觉令牌的新颖方法。该技术解决了使用多视角产生的冗余令牌问题,这可能导致计算成本高昂。CoVeR是一种确定性的、无需训练的选择器,它使用令牌坐标来确保场景的完整空间覆盖,同时遵守确切的令牌预算,克服了先前基于重要性或体素化方法的局限性。实验表明,CoVeR在三维推理基准测试中显著优于现有的最先进方法,在大幅减少令牌数量的同时实现了高性能。 AI

影响 通过显著降低计算负载而不牺牲性能,从而实现视觉语言模型(VLM)中更高效的三维推理。

排序理由 该集群描述了一篇详细介绍改进视觉语言模型(VLM)新颖方法的研究论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的CoVeR方法为视觉语言模型(VLM)中的三维推理剪枝视觉令牌

本文如何被排名

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇详细介绍改进视觉语言模型(VLM)新颖方法的研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
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
2 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu, Sreyas Mohan, Wei Ye, Dilin Wang, JQ Huang, Rakesh Ranjan, Aviral Chharia, Fernando De la Torre ·

    CoVeR:基于覆盖率的VLMs多视图3D推理的Token剪枝

    arXiv:2609.08345v1 Announce Type: cross Abstract: Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotated 3D data. However, it produces thousands of redundant visual tokens whose cost …

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    CoVeR: 基于覆盖率的VLMs多视图3D推理的Token剪枝

    CoVeR is a training-free spatial token selector that preserves 3D reasoning performance by enforcing exact budgets and full scene coverage across multi-view visual tokens.