Rohun Agrawal

prof_pic.jpg

rohun.agrawal[at]columbia[dot]edu

I’m a Computer Science PhD student at Columbia co-advised by Micah Goldblum at Columbia and Pavel Izmailov at NYU. I recieved my B.S. in Applied and Computational Mathematics from Caltech where I worked with Georgia Gkioxari on visual reasoning and in Katie Bouman’s lab on imaging inverse problems.

My current interests revolve around planning, exploration, and visual reasoning.

I’ve also interned at Apple training large video models, and at the NASA Jet Propulsion Laboratory calibrating GPR models.


Publications

  1. vadar.png
    Visual Agentic AI for Spatial Reasoning with a Dynamic API
    D. Marsilli*R. Agrawal*, Y. Yue, and G. Gkioxari
    Computer Vision and Pattern Recognition Conference (CVPR), 2025
  2. mars.png
    Holistic Mapping of the Present-day Martian Seasonal CO2 Frost: Part 1
    S. Diniega, G. Doran, S. Lu, M. Wronkiewicz, J. Widmer, R. Agrawal, and U. Rebbapragada
    Planetary Science Journal, 2025
  3. apls.png
    Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval
    R. Agrawal, and O. Leong
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023