报告时间：2024年7月12日（星期五）上午10：00

报告地点：广州大学城华南理工大学软件学院B7-403

主持人：黄翰 教授

报告题目：Towards Urban General Intelligence Through Urban Foundation Models

报告摘要：

Machine learning techniques are now integral to the advancement of intelligent urban services, playing a crucial role in elevating the efficiency, sustainability, and livability of urban environments. The recent emergence of foundation models such as ChatGPT marks a revolutionary shift in the fields of machine learning and artificial intelligence. Their unparalleled capabilities in contextual understanding, problem solving, and adaptability across a wide range of tasks suggest that integrating these models into urban domains could have a transformative impact on the development of smart cities. This talk will provide an overview of the latest advancements in Urban Foundation Models (UFMs). We will then present our recent practices with UFMs, including LLM-based urban knowledge acquisition, few-shot spatiotemporal forecasting, and generalizable decision-making. Additionally, to drive progress in this field, we will introduce a promising framework aimed at the future realization of UFMs.

报告人：刘浩

个人简介：

Dr. Hao Liu is currently an assistant professor at the AI Thrust Area in the Information Hub of The Hong Kong University of Science and Technology (Guangzhou). Previously, he was a senior research scientist at Baidu Research, working closely with product teams of Baidu Maps, AI Cloud, and Newsfeed. He received his Ph.D. degree from the CSE department of HKUST in 2017. His general research interests are in data mining and big data analytics, with a special application focus on urban intelligence. He frequently serves as a program committee member for conferences such as KDD, NeurIPS, ICLR, ARR and as a reviewer for prestigious journals, including TKDE, TKDD, TIST, TBD, and Transportation Research Part C. He co-organized the KDD Cup 2019 regular machine learning challenge. Many of his research outputs have been deployed on real-world products/projects, such as Baidu Maps, DiDi Chuxing, and Xinhua News Agency happiness index.

总编：黄翰

责任编辑：雷墨鹥兮

时间：2024年7月10日