Abstract
The advent of Al agents based on language models (e.g., ChatGPT) have received significant attention from the whole society. As researchers in this field, we are presented with a unique blend of opportunities and challenges to integrate these agents into real-world applications. Toward this ambitious goal, my talk will first explore research on enabling multiple agents to collaborate and achieve a shared goal within the Minecraft environment. Then l will discuss enhancing the robustness of these agents by accurately measuring uncertainty. Lastly, I will outline prospective avenues for future research, and share some wisdom on how to excel in research as an undergraduate, based on my experience of working with undergraduate students.
Biography
Chen Zhao is an Assistant Professor of Computer Science at NYU Shanghai. He is also affiliated at the Center for Data Science, New York University. He was a postdoctoral researcher at New York University, mentored by Prof. Kyunghyun Cho and Prof. He He. And he received Ph.D. at University of Maryland, College Park, advised by Prof. Jordan Boyd-Graber and Prof. Hal Daumé lll. Professor Zhao's main research interest is in natural language processing, in which the goal is to equip natural language intelligent agents with reasoning capacities and make them reliable and robust in real scenarios.