Aryan Mishra

Hi, I am Aryan, a Ph.D. student in Statistics at the University of Maryland, where I am advised by Dr. Lizhen Lin.

Previously, I worked as a researcher at the National Institute of Standards and Technology (NIST), contributing in Generative A.I research. I hold a Master of Engineering in CS and Robotics from the MAGE program, where I developed a strong foundation in control theory, deep learning, computer vision, and applied robotics.

Email  /  Linkedin  /  Scholar  /  Resume  /  Github

Research

I'm interested in Graph Informational Flow, Geometrical Deep Learning , Bayesean Machine Learning and their applications.

We propose Schreier-Coset Graph Rewiring (SCGR), a group-theoretic method that provably mitigates over-squashing in GNNs by creating low-resistance pathways for long-range information flow.