Hello! I’m a fourth-year PhD Candidate at the Penn State College of Information Sciences and Technology, advised by Prof. Dongwon Lee.

As a member of the PIKE Research Group, my research is focused on enhancing the Visio-linguistic grounding and reasoning capabilities of Multi-modal Large Language Models (MLLM). Particularly, I’m interested in understanding the challenges MLLMs face while interpreting cross-modal relationships in domain-specific generation tasks. I’m also exploring the prevalence of AI-generated content across online discourses such as news media, to better inform usage and detection strategies of these models.

In the past, I have had the opportunity to do internships at Optum AI (UnitedHealthGroup), The Washington Post, Ford Motor Company, and other Computer Vision startups. I’m always open to collaboration and research discussions on topics related to Vision & Language tasks. Feel free to drop me an email or ping me on LinkedIn if you wish to get in touch with me!