PulseAugur
中
实时 08:22:54
Deutsch(DE) REKI: Registering Knowledge in VLAs

新型REKI VLA模型通过内存功能平衡性能与尺寸

研究人员推出REKI,一个拥有24亿参数的视觉语言动作模型(VLA),在性能和尺寸之间取得了新的平衡。REKI在公开数据上进行了预训练,并引入了一个使用寄存器令牌的内存机制,以访问最近的 past 信息,据报道这可以减少振荡并提高模拟和真实机器人上的成功率。该模型的设计优先考虑了训练和推理的效率,其创建者已发布了完整的代码和预训练权重。 AI

影响 该模型的高效设计和内存功能可能会影响未来机器人和具身AI系统的发展。

排序理由 该集群描述了一篇介绍新颖模型架构及其在基准测试中性能的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新型REKI VLA模型通过内存功能平衡性能与尺寸

本文如何被排名

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇介绍新颖模型架构及其在基准测试中性能的新研究论文。[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
model release, paper, product
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.LG TIER_1 Deutsch(DE) · Juliette Marrie, Paul Pacaud, Adrien Ramanana Rahary, Shizhe Chen, Moritz B\"ohle ·

    REKI: 在视觉语言模型中注册知识

    arXiv:2610.22178v1 Announce Type: cross Abstract: We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plus, RoboTwin Clean2Rand and RoboCasa365, it is outp…