I am a Ph.D. student in the Department of Electrical and Computer Engineering at Texas A&M University. I am advised by Dr. Dileep Kalathil. My research interests focus on reinforcement learning, distributionally robust optimization, and large language model (LLM) alignment.

Before, I attended University of Illinois at Urbana-Champaign. In 2020, I received my B.S. degree in Computer Science and Statistics as well as in Actuarial Science (double major).

Curriculum Vitae

Publications

Preprints

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
Zaiyan Xu, Sushil Vemuri, Kishan Panaganti, Dileep Kalathil, Rahul Jain, Deepak Ramachandran
[paper]

Conference Papers

Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage
Kishan Panaganti, Zaiyan Xu, Dileep Kalathil, Mohammad Ghavamzadeh
L4DC, 2025
[paper]

Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning
Zaiyan Xu*, Kishan Panaganti*, Dileep Kalathil
AISTATS, 2023
[paper]

Robust Reinforcement Learning Using Offline Data
Kishan Panaganti, Zaiyan Xu, Dileep Kalathil, Mohammad Ghavamzadeh
NeurIPS, 2022
[paper]

Distributionally Robust Behavioral Cloning for Robust Imitation Learning
Kishan Panaganti*, Zaiyan Xu*, Dileep Kalathil, Mohammad Ghavamzadeh
CDC, 2023
[paper]

(* equal contribution)

Work Experience

Mitsubishi Electric Research Laboratories	Cambridge, MA
Research Intern	May 2023 - Aug. 2023

National Center for Supercomputing Application	Champaign, IL
Undergraduate Researcher (NCSA SPIN Program)	Jun. 2019 - May 2020

Awards

NeurIPS Top Reviewer	2023
Department of Electrical and Computer Engineering Graduate Merit Fellowship, Texas A&M University	2020
Willis Towers Watson Actuarial Science Scholarship, Dept. of Mathematics, University of Illinois at Urbana-Champaign	2018

Academic Services

Conference Reviewer: ICLR (2024, 2025), NeurIPS (2023 Top Reviewer, 2024), ICML (2023, 2024, 2025), AISTATS (2023, 2024), American Control Conference (2023), IEEE Conference on Decision and Control (2023, 2024, 2025), L4DC (2023, 2024, 2025)

Invited Talks

Distributionally Robust Reinforcement Learning
NICO Reading Group, Northwestern University
September 2023