I am a graduate student with the Department of Computer Science at the University of Illinois Chicago. I am advised by Dr. Natalie Parde as part of the Natural Language Processing Lab.
My journey has been an explorative one, where I have delved into a few exciting fields across engineering. At the graduate level, I have conducted research on human-robot interaction and bias across published news. My master's thesis was on the detection and analysis of vulnerabilities among automated fake news detectors. More recently I have been interested in how artificial intelligence can learn from human intelligence. I've analyzed spike patterns in mice through the study of computational neuroscience and interpret latent hidden states in recurrent neural networks (RNNs) in neuroAI.
Currently, I have started working on interpretability of AI models and making them safer. I have also worked on applying NLP techniques to medical data and am currently (on a grant from ARPA-H ) utilizing graph neural networks to identify key patterns in patient history.
