I am a PhD candidate in EECS, advised by Dr. Pete Szolovits in the Clinical Decision Making Group (MEDG). My research aims to advance the field of machine learning for health through the power of Large Language Models, using semi-supervised and multi-modal learning. During my PhD, I worked towards several challenges such as 1) leveraging clinical knowledge over heterogeneous features to make models robust to changes in hospital practices over time, 2) creating pipelines for smarter feature selection from health data for use in ML models, 3) disease prediction with noisy and often missing data and 4) making machine learning models more privacy-preserving. By applying techniques from computer vision, natural language processing, classical machine learning and differential privacy, I develop effective and robust frameworks to address challenges associated with making predictions using (mostly) medical data. I also have experience working with language, vision and speech data in the general domain. You may access my CV if interested.
I am on the job market for Research/ Applied Scientist/ Postdoc roles.
I have spent 3 wonderful summers interning at Google Research and Bosch Center for AI (BAI). exploring entity extraction, visual question answering and differentially private training of large transformer-style models. Previously, I received a B.S. in Computer Science from Florida International University, where I was advised by Profs. Mark Finlayson and Christine Lisetti.
I am a recipient of the Frederick (1953) and Barbara Cronin Fellowship at MIT and presented with the honor of being a Graduate Woman of Excellence. I had the honor of being banner marshal for the Class of 2017 for the College of Engineering and Computing and named as the Outstanding Undergraduate in Computer Science in recognition of academic achievement and service to the department.
In my free time, I enjoy practicing and teaching yoga, photography, drawing and cooking.