CURIO:好奇心驱动的测试时学习用于开放式发现
TLDR
CURIO 以内在好奇心世界模型增强测试时强化学习,改进开放式数学发现与单细胞去噪。
评分理由
The paper presents a clear framework and strong empirical results across tasks and model scales, including diversity metrics. However, its world model is limited to hidden-state transition prediction for curiosity bonuses, not a full generative or interactive world simulator, and the abstract omits explicit limitations.
Read-first 评分解释
综合优先阅读分 22.1,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 21。
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:158。