2024年9月23日10:00至11:30，香港中文大学（深圳）数据科学学院（SDS）将在道远楼103举办加州大学河滨分校（UCR）电子与计算机工程系的科研分享及硕士、博士项目招生宣讲会。

此次宣讲会由UCR电子与计算机工程系的助理教授朱英伦主讲。朱教授将介绍其研究成果及UCR电子与计算机工程的招生信息，并与现场同学进行互动交流和答疑。

宣讲会详情

■ 时间
2024年9月23日（星期一）10:00至11:30

■ 地点
道远楼103

■ 语言
英文

■ 主讲人介绍

朱英伦
美国加州大学河滨分校

Dr. Yinglun Zhu is an assistant professor in the ECE department at the University of California, Riverside; he is also affiliated with the CSE department, the Riverside Artificial Intelligence Research Institute, and the Center for Robotics and Intelligent Systems. His research focuses on machine learning, particularly in developing efficient and reliable learning algorithms and systems for large-scale, multimodal problems. His work not only establishes the foundations of various learning paradigms but also applies them to practical settings, addressing real-world challenges. His research has been integrated into leading machine learning libraries such as Vowpal Wabbit and commercial products like Microsoft Azure Personalizer Service.

■ 讲座内容

10:00 - 10:40 
Part 1 - Research Talk 
Efficient Sequential Decision Making with Large Language Models

There is a growing interest in extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former approach suffers from the computational burden of gradient updates, and the latter approach does not show promising results. We developed a new approach that leverages online model selection algorithms to efficiently incorporate LLMs agents into sequential decision making. Statistically, our approach significantly outperforms both traditional decision making algorithms and vanilla LLM agents. Computationally, our approach avoids the need for expensive gradient updates of LLMs, and throughout the decision making process, it requires only a small number of LLM calls. We conduct extensive experiments to verify the effectiveness of our proposed approach. As an example, on a large-scale Amazon dataset, our approach achieves more than a 6x performance gain over baselines while calling LLMs in only 1.5% of the time steps.

10:45 - 11:30 
Part 2 - Information Session 
UCR Graduate Programs

Dr. Yinglun Zhu will introduce the University of California, Riverside, highlighting the admission process and career prospects of the academic programs—specifically the MS and PhD programs in the ECE department.

■ 报名链接
请感兴趣的同学扫描下方二维码并填写问卷报名：https://www.wjx.top/vm/rXaxdnF.aspx