English(EN) How do Transformers Perform Low-Level Control In-Context?

Transformer 展示了上下文控制动态系统的能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员探索了基于 Transformer 的神经网络通过上下文学习来执行不稳定、非线性动态系统的低级控制的能力。通过在专家控制器轨迹上训练 GPT-2 风格的架构，模型展示了稳定倒立摆和双连杆机器人等系统的能力，即使在系统参数未知的情况下也是如此。研究发现，增加上下文长度通常会提高策略性能，并且模型可以泛化到分布外系统。 AI

影响展示了大型语言模型在特定训练数据有限的情况下执行复杂控制任务的潜力。

排序理由详细介绍 Transformer 模型新应用的论文。[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 →

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; 详细介绍 Transformer 模型新应用的论文。[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, 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: 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]

arXiv cs.LG TIER_1 English(EN) · Ebonye Smith, Aidan Andrews, Phoenix Wilson, Alexis Frias, Ayush Pandey, Gireeja Ranade · 2026-11-06 05:00

Transformer 如何在上下文（In-Context）中执行低级控制？

arXiv:2611.07291v1 Announce Type: new Abstract: One of the remarkable abilities of Transformer-based neural networks is in-context learning. This motivates us to think about "in-context" control. Can we control a system knowing only (1) that it belongs to a particular family of s…

本文如何被排名

报道来源 [1]

Transformer 如何在上下文（In-Context）中执行低级控制？

相关实体

相关话题