基于LiDAR的令牌选择可大幅降低自动驾驶模型的计算量

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员开发了一种名为几何感知令牌选择（GATS）的新方法，用于自动驾驶模型，通过选择性地处理图像令牌，显著降低了计算负荷。通过利用LiDAR和雷达数据在主视觉骨干网络之前识别相关图像块，GATS减少了天空或建筑物等无关数据。这种方法可以大幅减少FLOPs，即使在10%的令牌预算下也观察到了性能提升，并且以一小部分计算成本优于密集模型。 AI

影响降低了自动驾驶系统的计算要求，可能支持更高效的实时处理。

排序理由详细介绍一种新的计算机视觉模型方法的论文。[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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新的计算机视觉模型方法的论文。[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: 1 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 [1]

arXiv cs.CV TIER_1 English(EN) · Zeping Zhang, Zhuoya Zhao, Robert Lagani\`ere · 2026-11-02 05:00

Let LiDAR Decide Where to Look: Geometry-Measured Token Selection for Efficient Sparse Latent World Models

arXiv:2610.40935v1 Announce Type: new Abstract: Vision-centric autonomous driving models encode thousands of image tokens per frame, yet most depict sky, buildings, or empty road---content irrelevant to planning. Worse, these tokens dilute the planner's attention: we show that ra…

本文如何被排名

报道来源 [1]

Let LiDAR Decide Where to Look: Geometry-Measured Token Selection for Efficient Sparse Latent World Models

相关实体

相关话题