arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

ACM SIGKDD Conference on Knowledge Discovery and Data Mining · 会议 · Data Mining

2026-06-19 至 2026-06-19 共收录 1
2402.14035 2026-06-19 cs.LG cs.AI 版本更新

Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts

委员会智慧:来自大型基础模型和领域专家的多样化蒸馏

Zichang Liu, Qingyun Liu, Yuening Li, Liang Liu, Anshumali Shrivastava, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao

机构 * Rice University(Rice大学) Google DeepMind(谷歌DeepMind) Google Inc(谷歌公司) University of California, Davis(加州大学戴维斯分校)

AI总结 针对基础模型向紧凑领域模型蒸馏时能力、架构和模态差异大的问题,提出DiverseDistill框架,通过可学习的问答机制和对齐异构教师输出,在推荐和视觉任务上恢复73-114%的性能差距。

Comments Accepted at the 1st Workshop on Resource-Efficient Learning and Knowledge Discovery (RelKD), KDD 2026

Journal ref Proceedings of the International Workshop on Resource-Efficient Learning and Knowledge Discovery (RelKD), KDD 2026

详情

展开后加载摘要…

URL PDF HTML 收藏