Chenguang S. Wang

I am currently a Postdoctoral Fellow at Virginia Tech, working under the supervision of Prof. Dawei Zhou. My research aims to enhance the robustness and controllability of Large Language Models (LLMs) by developing effective post-training strategies, retrieval-augmented frameworks, and multi-modal reasoning techniques, particularly for real-world applications such as disaster response and decision support systems.

I received my Ph.D. Degree from Stony Brook University, where I was advised by Prof. Susu Xu. Prior to that, I earned a Master of Science in Computer Science from Stevens Institute of Technology, where I worked with Prof. Xiaojiang Du, and a Bachelor of Science in Computer Science from Xi’an Jiaotong University. From 2024 to 2025, I was also a Graduate Visiting Scholar at Johns Hopkins University.

My research interests broadly lie in Machine Learning (ML), Natural Language Processing (NLP), and Large Language Models (LLMs).
More specifically, my recent research focuses on:

• (ii) Post-training and Alignment for LLMs (Mosaic-IT, RuleR)

• (i) LLM Applications in Disaster Management (CrisisNLP, FLARE)

• (iii) Multi-Modal Large Language Models (MLLMs) (TRIG, CaughtCheating)

I am also actively exploring Retrieval-Augmented Generation (RAG) (FLARE), LLM-based Agents (StreetDesinger), and Reinforcement Learning (RL).

I am particularly interested in research collaborations and opportunities to advance impactful AI research. I welcome conversations around collaborative projects and broader research opportunities in both academic and industry settings.