报告题目：Generative Retrieval from Search to Recommendation: Recent Advances and Directions
报告人：任昭春 荷兰莱顿大学
报告摘要：
Generative retrieval is reshaping search and recommendation by embedding corpus knowledge within generative models. This unified framework replaces traditional indexing by directly mapping queries and user contexts to document or item identifiers. In this talk, I will highlight key advancements, including innovative identifier design, joint training frameworks that integrate auto-encoding with retrieval, and scalable inference strategies. These approaches bridge the gap between search and recommendation by leveraging semantic representations that capture both content-based and collaborative signals. Drawing on recent studies, I will provide a concise overview of the core concepts, methodological innovations, and practical applications driving this emerging field, while also introducing the remaining challenges and proposing directions for future research.
报告人简介：
Dr. Zhaochun Ren is an Associate Professor at Leiden University, the Netherlands. He is interested in information retrieval and natural language processing, with an emphasis on conversational artificial intelligence, recommender systems, and information retrieval. He aims to develop intelligent agents that can address complex user requests and solve core challenges in NLP and IR towards that goal. His research has been recognized with multiple awards at RecSys, SIGIR, WSDM, EMNLP, and CIKM. Prior to joining Leiden, he was a Professor at Shandong University and a Research Scientist at JD.com.
报告时间：2025年9月15日（星期一）上午10:00
报告地点：吉林大学正新楼三楼报告厅
主办单位：吉林大学人工智能学院
