arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

ACM SIGIR Conference on Research and Development in Information Retrieval · 会议 · Information Retrieval

2026-05-08 至 2026-05-08 共收录 1
2605.06403 2026-05-08 cs.CL cs.IR

GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation

GATHER:面向零样本细胞类型注释的收敛性超实体检索

Zhonghui Zhang, Feng Jiang, Shaowei Qin, Jiahao Zhao, Min Yang

机构 * Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology(深圳先进技术大学人工智能研究院) Software College, Northeastern University(东北大学软件学院) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)

AI总结 GATHER通过全局多源图遍历识别拓扑收敛点,以高信息超实体捕捉实体协同,无需LLM参与检索,提升零样本细胞类型注释效率。

Comments Accepted to SIGIR 2026. 2 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏