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.
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
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
Zilu Jiang, Zexin Xu, Zilong Pan, Jingwen He, Kui Xie
Languages
Jingwen He, Bihui Jin, Zexin Xu, Danhui Zhang
Journal of Online Learning Research