Eshika Khandelwal

I am a first year PhD student at the Tübingen AI Center, University of Tübingen, advised by Prof. Hilde Kühne. I work on structured decoding for Vision-Language Models, with the goal of making them reliably produce machine readable outputs (e.g., bounding boxes, JSON) for vision tasks and agent based Al systems.

Previously, I completed my B.Tech in Computer Science with an MS by Research in Computational Linguistics (dual degree) at the International Institute of Information Technology Hyderabad, where I worked with Prof. Makarand Tapaswi at the Centre of Vision Information Technology.