主 讲 人
赵晨
主 讲 人:赵晨
主 持 人: 肖仰华,复旦大学计算与智能创新学院教授,上海市数据科学重点实验室主任
时 间: 2025年10月30日,14:00-16:00
地 点: 复旦大学江湾校区二号交叉学科楼A3009
主办单位:上海市数据科学重点实验室
直播链接:
报告标题
Towards better agentic search systems
报告摘要
Agentic search systems, such as OpenAI’s Deep Research, have recently attracted significant attention. Despite their promising capabilities, current systems remain far from reliable: one of the most pronounced limitations is their tendency to retrieve irrelevant or redundant evidence. In this talk, I will present our recent efforts toward building better agentic search systems from several perspectives: (1) improving the breadth and diversity of retrieved information, (2) efficiently discovering long-tail knowledge, and (3) exploring text diffusion models as an alternative architectural paradigm. I will conclude with a discussion of future directions and open challenges.
讲者简介
赵晨老师2023年秋加入上海纽约大学,他本科毕业于浙江大学,博士毕业于马里兰大学,并曾在纽约大学从事博士后研究。其主要研究方向为自然语言处理,致力于推动基于大模型的智能体与外部工具协同工作的能力发展,并使其在真实场景中更加可靠和可解释。 赵晨老师在ACL,EMNLP,ICML,ICLR等自然语言处理和机器学习领域顶级会议中发表多篇论文。

