Varun Sreedhara Bhatt

Ph.D. Student, ICAROS Lab, University of Southern California

PhotoColor_2023.jpg

I am a Ph.D. student with Prof. Stefanos Nikolaidis in the Computer Science department at the University of Southern California. Prior to my Ph.D., I completed my M.Sc. at the University of Alberta with Prof. Michael Buro and B.Tech at the Indian Institute of Technology Bombay.

My main research goal is to build robust and generalizable intelligent agents that work well alongside humans and other intelligent agents. Towards that end, I have been working on methods to generate diverse and challenging environments via a combination of generative models and quailty diversity optimization.

Outside of research, I mostly spend time on gaming and occasionally on hiking and travel. I am also a fan of puzzles, so there is a good chance you will find me solving variant sudokus during work breaks!

Selected publications

  1. qdig.png
    Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies
    Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu, Varun Bhatt, Shihan Zhao, Henry Chen, Bryon Tjanaka, Minjune Hwang, Akanksha Saran, Daniel Seita, Aaquib Tabrez, and Stefanos Nikolaidis
    (under review), 2025
  2. planqd.png
    Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models
    Siddharth Srikanth, Varun Bhatt , Boshen Zhang, Werner Hager , Charles Michael Lewis , Katia P. Sycara, Aaquib Tabrez, and Stefanos Nikolaidis
    (under review), 2025
    arXiv
  3. dsas.gif
    Surrogate Assisted Generation of Human-Robot Interaction Scenarios
    Varun Bhatt, Heramb Nemlekar , Matthew C. Fontaine, Bryon Tjanaka , Hejia Zhang, Ya-Chuan Hsu, and Stefanos Nikolaidis
    In Proceedings of the Conference on Robot Learning (CoRL) , 2023
    arXiv Code Presentation
  4. dsage.png
    Deep Surrogate Assisted Generation of Environments
    Varun Bhatt, Bryon Tjanaka , Matthew C. Fontaine, and Stefanos Nikolaidis
    In Advances in Neural Information Processing Systems (NeurIPS) , 2022
    arXiv Code Presentation Website