Publications

My research focuses on advancing the capabilities and security of Large Language Models (LLMs), with particular emphasis on code understanding, robustness against adversarial attacks, system integration, and educational applications. Current research directions include LLM-based code generation, attack/defense mechanisms for LLMs, development of reliable LLM-powered systems, and AI-enhanced educational technology.

Towards a robust and generalizable embodied agent

Chan Hee Song, Jiaman Wu, Ju-Seung Byun, Zexin Xu, Vardaan Pahuja, Goonmeet Bajaj, Samuel Stevens, Ziru Chen, Yu Su

Alexa Prize SimBot Challenge Proceedings

AmazonPDF

Towards a robust and generalizable embodied agent

Chan Hee Song, Jiaman Wu, Ju-Seung Byun, Zexin Xu, Vardaan Pahuja, Goonmeet Bajaj, Samuel Stevens, Ziru Chen, Yu Su

Embodied AI Workshop at CVPR

CVPRPDF

Exploring the Role of Artificial Intelligence in Facilitating Assessment of Writing Performance in Second Language Learning

Zilu Jiang, Zexin Xu, Zilong Pan, Jingwen He, Kui Xie

Languages

LanguagesPDF

2023

Measuring Elementary Students’ Behavioral Engagement in Web-based Science Inquiry Learning

Jingwen He, Bihui Jin, Zexin Xu, Danhui Zhang

Journal of Online Learning Research

JOLRPDF

2022