'Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control' accepted to CoRL 2025 as an oral presentation (top 5.65%); 'Harnessing Input-adaptive Inference for Efficient VLN' accepted to ICCV 2025; named as an outstanding reviewer (top 5%) at CVPR 2025; 'Do Visual Imaginations Improve Vision-and-Language Navigation Agents?' accepted to CVPR 2025 (22.1%).
Research Experience
Works as an ML engineer at Ford Motor Company, primarily on perception features for automated driving using camera images and LiDAR point clouds.
Education
Currently a Ph.D. student at Oregon State University under Dr. Stefan Lee; previously graduated with a master's degree from the University of Florida; worked at the Indian Institute of Science under Prof. K R Ramakrishnan at the CVAI lab on table-top touch-interface applications using a projector-camera based setup.
Background
Primary research interests lie in the intersection of vision and language learning, focusing on problems arising from a lack of grounding, lack of annotated or domain-specific data, and distributional differences between test and training data. Recently, drawn to problems motivated by cognitive science.
Miscellany
Enjoys playing/watching soccer, kickboxing, hiking (especially waterfall hikes), and practically any outdoor sport in free time.