Amartya is a PhD student in Computer Science at Virginia Tech, specializing in Language Models and multimodal data. During my Master’s, I worked with Vision-Language Models (VLMs) to predict structured Scene Graph relationships without additional fine-tuning. My research focuses on enhancing the reasoning capabilities of Large Language Models (LLMs) and VLMs for various downstream tasks. Currently, I contribute to the Community Empowering Pandemic Prediction and Prevention from Atoms to Societies (COMPASS) project, which takes an interdisciplinary approach to pandemic preparedness.