PulseAugur
中
实时 06:58:01
English(EN) APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action Models

新的APS-VLA框架通过修剪视觉令牌加速机器人控制

研究人员开发了APS-VLA,一个旨在提高机器人操作中使用的视觉-语言-动作(VLA)模型效率的新框架。该方法通过使用轻量级的决策影响估计器来修剪视觉令牌,而视觉令牌通常是推理延迟的瓶颈。该估计器学习根据当前观察、语言指令和机器人本体感觉来选择关键令牌,而无需更改核心VLA模型。实验表明,APS-VLA可以显著减少推理时间,在真实机器人任务上实现1.47倍的加速,同时保持与未修剪模型相当的成功率。 AI

影响 该框架通过减少视觉-语言-动作模型的计算负载,可能带来更快、响应更灵敏的机器人系统。

排序理由 这是一篇详细介绍改进AI模型效率新方法的论文。[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 →

新的APS-VLA框架通过修剪视觉令牌加速机器人控制

本文如何被排名

Signal score
36 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一篇详细介绍改进AI模型效率新方法的论文。[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
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]

  1. arXiv cs.AI TIER_1 English(EN) · Xiaoyang Xing, Chun-Mei Feng, Anthony Cohn, Xiaoliang Gong, Asoke Nandi ·

    APS-VLA:面向高效视觉-语言-动作模型的动作引导和面向未来的令牌剪枝

    arXiv:2611.13030v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have demonstrated strong generalization in robotic manipulation, yet processing dense visual tokens often incurs high inference latency. Visual token pruning offers a practical way to reduce thi…