I'm a postdoctoral fellow at the Harvard School Of Engineering And Applied Sciences (SEAS), working with David Parkes. I recently completed my PhD at the Computational Science and Engineering department at Georgia Institute of Technology, where I was incredibly fortunate to be advised by Hongyuan Zha.
My primary research interest lies in developing human-centered AI - tools, agents, and frameworks that can drive progress on challenging problems across diverse domains, quickly adapt to evolving human needs and achieve alignment with human values. Along this direction, I have focused on building generalizable AI for networked and multi-agent systems, with an eye on broad, interdisciplinary applications of social and economic concerns. Specifically, my current work is centered around integrating machine learning techniques (graph machine learning, reinforcement learning and generative modeling in particular) with human behavioral concepts, through the lens of network science, game theory, and social learning theory, to make progress towards this goal of building AI that is beneficial to humans.
- December 2022: Our work on "Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph Models" was accepted and presented at Neurips Temporal Graph Learning Workshop.
- August 2022: I gave an invited talk on "Learning from Interactions in Networked Systems" as a part of Beneficial AI seminar series at the Center for Human-Compatible Artificial Intelligence (CHAI), UC Berkeley.
- May 2022: Our work on "Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning" was accepted and presented at AAMAS 2022.
- April 2022: Our work on "CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games" was accepted and presented at ICLR 2022.