I am a 5th-year Ph.D. student at the Computer Science Department of University of Maryland, College Park, where I am advised by Prof. Hal Daumé III. I graduated from Columbia University with M.S. in Computer Science, and Sun Yat-Sen University with B.S. in Computational Mathematics.

I am broadly interested in studying problems related to trustworthiness in multimodal setting, aiming to enhance human-centered AI. My research focuses on equipping visual-language models with self-reasoning and self-improvement capabilities to better serve human needs. This includes:
(i) Correcting hallucinations and communicating uncertainties
(ii) Fostering pragmatic understanding by simulating human behavior
(iii) Generating faithful explanations
(iv) Visual-language alignment for long context

News

• [Jun 2025] Excited to start research internship at Microsoft Semantic Machines!
• [Feb 2025] New paper on Can Hallucination Correction Improve Video-Language Alignment? Accepted by ACL 2025.
• [Nov 2024] I’m going to EMNLP 2024 in person, to give a presentation for this paper. Let’s chat!
• [Feb 2024] New paper on Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Alternatives, accepted by EMNLP 2024 main conference (Oral). Project Website
• [Oct 2023] New paper on Hallucination Detection for Grounded Instruction Generation, accepted by EMNLP 2023. Project Website
• [Dec 2022] New paper on Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models. Accepted by ACL 2023, and ICML ToM Workshop 2023 (received Outstanding Paper Award). Code and dataset released on Project Website