arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

2025-11-20 至 2025-11-20 共收录 2
2511.15507 2025-11-20 cs.LG cs.DS stat.ML

Sample-Adaptivity Tradeoff in On-Demand Sampling

按需采样中的样本复杂度与轮次复杂度权衡

Nika Haghtalab, Omar Montasser, Mingda Qiao

机构 * University of California, Berkeley(加州大学伯克利分校) Yale University(耶鲁大学) University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

AI总结 本文提出了一种新的框架OODS,用于在按需采样中平衡样本和轮次复杂度,实现了近最优的样本复杂度和轮次复杂度界。

Comments 50 pages, to appear at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20098 2025-11-20 cs.CL cs.AI

Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning

Yajie Li, Albert Galimov, Mitra Datta Ganapaneni, Pujitha Thejaswi, De Meng, Priyanshu Kumar, Saloni Potdar

机构 * College of Information and Computer Sciences, University of Massachusetts Amherst(信息与计算机科学学院,马萨诸塞大学阿默斯特分校) Apple(苹果公司)

Comments Accepted to EMNLP 2025 Industry Track

详情

展开后加载摘要…

URL PDF HTML 收藏