I’m a fourth-year undergratuate at IIIT Hyderabad, studying computer science and computational linguistics. I’m currently an undergraduate researcher under Dr. Vinoo Alluri, and Dr. Makarand Tapaswi.
My research work currently centers on better understanding and explaining the way deep learning models process audio specifically, and information in general.
I have varied interests ranging across mathematics, computing, language, and music. Currently, I’m particularly interested in interpretability, multi-modal deep learning, and auditory processing in the human brain.
Researching on the interpretability of deep learning systems for audio tasks under Dr. Vinoo Alluri (Music Cognition Group, Cognitive Science Lab) and Dr. Makarand Tapaswi (Video Language Group, Center for Visual Information Technology)
Worked on studying and implementing algorithms for fast, single-stage scene text spotting for deployment on embedded systems.
Worked on XFCE's file manager Thunar, adding features such as undo/redo, file counts for folders, and a new gallery view.
Currently pursuing a dual degree, B.Tech in Computer Science and MS in Computational Linguistics by Research, at IIIT Hyderabad.