Presented dissertation work at the Doctoral Consortium at FG 2025; awarded the Provost's Dissertation Completion Fellowship for Fall 2025 at Pitt; delivered a guest lecture on Multimodal LLMs for the CS 2750 course at Pitt; received the Outstanding Reviewer Award at FG 2024; published multiple papers on multimodal machine learning, covering domains such as Computer Vision, Speech Processing, and Natural Language Processing.
Research Experience
Worked as a Computer Vision Researcher at Playment (acquired by Telus International), developing and deploying interactive semantic segmentation models (including raster-to-vector conversion).
Education
PhD - University of Pittsburgh, School of Computing and Information, supervised by Prof. Jeff Cohn; MS - IIIT Hyderabad, supervised by Prof. Ramanathan Subramanian and Prof. Mohan Kankanhalli.
Background
PhD candidate at the University of Pittsburgh's School of Computing and Information, focusing on Multimodal Machine Learning. Interests include using facial expressions, voice prosody, body pose, and speech for applications in affective computing and how these multimodal behaviors shape day-to-day human communication.