Hi!

I am an MSc student in Statistics at the University of Chicago, interested in ML and AI with a focus on understanding and improving out of distribution generalization and robustness under distribution shift. I like to think about these problems through a statistical and probabilistic lens.

Right now I am mostly focused on

• Probabilistic modeling and inference
  Working with Bayesian models for uncertainty quantification and studying their limitations under distribution shift, with the goal of understanding when they fail and how to make them more reliable.
• Trustworthy AI agents
  Building and studying agents that use tools and act in complex environments, using reinforcement learning and synthetic evaluation setups to probe failure modes, improve robustness, and make their behavior more predictable and controllable.
• Applications to life sciences
  Developing modern statistical and geometric methods for neuroscience and healthcare data, such as brain networks and other high dimensional signals, with a focus on uncertainty quantification and out of distribution detection, so that models can flag when they should not be trusted and still give insights that are scientifically meaningful and practically useful.

If this overlaps with what you are working on or thinking about, feel free to send me an email to chat or explore possible collaborations.

Publications