I am a PhD student at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Rajesh P. N. Rao. My research focuses on building agents that can perceive, reason, and act robustly in complex environments. I work at the intersection of reinforcement learning, world models, and Neuro-AI. Recently, my work has explored brain-inspired architectures and machine learning algorithms based on Active Predictive Coding for hierarchical world models, compositional generalization, and planning. I have also dabbled with RL fine-tuning for multimodal tool-using agents, during my internship at Amazon.

More broadly, I am interested in how ideas from neuroscience such as prediction errors, actions, cognitive maps, and episodic memory - can inform the design of safer, more interpretable, and more capable AI systems.