Chenguang S. Wang

I am a Ph.D. candidate at Stony Brook University, advised by Prof. Susu Xu.
I began my academic journey with a Bachelor of Science in Computer Science from Xi’an Jiaotong University in 2020, followed by a Master of Science in Computer Science at Stevens Institute of Technology in 2023, where I worked with Prof. Xiaojiang Du.
From 2024 to 2025, I was a Graduate Visiting Scholar at Johns Hopkins University.

If you are looking for a highly motivated researcher with a strong background in LLMs, NLP, and AI, and a passion for advancing intelligent systems for real-world impact, I would be thrilled to have an opportunity to chat with you about postdoctoral or full-time AI Researcher opportunities!

My research interests broadly lie in Machine Learning (ML), Natural Language Processing (NLP), and Large Language Models (LLM).
More specifically, my recent research focuses on:
(i) LLM applications in Disaster Management (CrisisNLP, FLARE);
(ii) Post-training for LLMs (Mosaic-IT, RuleR);
(iii) Multi-Modal LLMs (MLLMs) (TRIG, CaughtCheating);
I am also interested in and now exploring RAG(FLARE), Agent (StreetDesinger), and RL.

I am open to collaborations and opportunities to continue advancing AI for impactful real-world applications.

News

Nov 17, 2025	One paper was selected as a LAW Workshop @ NeurIPS 2025 Spotlight paper! CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning. One paper was accepted by UrbanAI Workshop @ NeurIPS 2025! From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation.
Sep 6, 2025	One paper was put on the arXiv: From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation.
Jun 23, 2025	One paper was put on the arXiv: CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning.
May 16, 2025	Two papers were accepted by ACL 2025! 1 From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs; 2 Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning;
Jan 24, 2025	I successfully passed the qualifying examination and advanced to Ph.D. candidacy at Stony Brook University.
Jan 22, 2025	One paper was accepted by NAACL 2025! RuleR: Improving LLM Controllability by Rule-based Data Recycling
Sep 16, 2024	I am excited to join Johns Hopkins University as a Visiting Scholar for a one-year fixed term.
Jul 14, 2024	One paper was accepted by International Journal of Disaster Risk Reduction! Near-real-time earthquake-induced fatality estimation using crowdsourced data and large-language models
Mar 5, 2024	One paper was accepted by International Journal of Disaster Risk Reduction! “Scalable and rapid building damage detection after hurricane Ian using causal Bayesian networks and InSAR imagery”
Jan 18, 2023	I arrived at Stony Brook University, officially beginning my journey as a Ph.D. student.
Dec 23, 2022	I completed my Master’s in Computer Science at Stevens Institute of Technology.
Aug 30, 2022	I received the Provost Doctoral Fellowship at Stevens Institute of Technology in recognition of my academic excellence.
Aug 25, 2022	My research project advised by Prof. Xiaojiang Du has won the ECE Research Scholarship Award.
Aug 23, 2021	I started my Master’s at Stevens Institute of Technology.