无须看见混沌即可学习混沌:自回归Transformer中全局动力学的外推
TLDR
小型自回归Transformer从受限参数轨迹训练后,可高保真外推至混沌与周期倍增级联。
评分理由
The paper presents compelling evidence that local training data can yield global dynamical extrapolation, supported by quantitative results like the Feigenbaum constant and causal attention analysis. However, all evaluations are on synthetic dynamical systems, and the paper does not address more general world modeling, real-world data, or interactive/R L settings.
Read-first 评分解释
综合优先阅读分 21.5,由主题、引用、图谱、方法、可复现性和近期性等信号加权得到。 原始总分保留为 11。
研究版图角色
前沿论文
排序敏感性
稳定性:volatile;排名波动范围:75。