TAG
#eye-tracking
0 篇评论 · 2 篇随笔
相关随笔
von Gugelberg: How people solve differed more by 'which item' than by how hard it was — Fukai Reads
An eye-tracking study of figural matrix problems by Helene M. von Gugelberg. Recording 300 people item by item, it reports that stronger reasoners build the answer before checking options, and that people differ more in how their approach changes across item positions than in how they react to difficulty.
Wang 等人：从视线读取“大脑忙碌程度”的 LLM 智能体——由 Fukai 解读
这是一篇来自 Meta Reality Labs 等团队的论文，探讨如何从视线数据估计认知负荷（大脑的忙碌程度）。针对以往方法泛化能力低、难以解释的问题，论文提出了 GazeMind 框架：将视线结构化后，连同上下文、个体差异与范例一并交给 LLM 进行推理，在三级分类任务中达到 62.73% 的准确率（比现有方法高出20个百分点以上）。
