Smayan A. Khanna

IMG_8041.jpg

Welcome to my personal website! I completed my B.S. in Physics with a minor in Computer Science and my M.S. in Computer Science at the University of Chicago, and I’m starting my Ph.D. in Data Science at UC San Diego this fall.

My research interests lie in AI for science (AI4Science), with a focus on graph learning and representation learning. I’ve worked on problems spanning molecular dynamics, computational neuroscience, and graph neural networks for coarse-graining physical systems. More broadly, I’m interested in how machine learning methods can be made to generalize effectively in scientific domains.

I’ve conducted research at MIT (with Prof. Jörn Dunkel), in UChicago’s Ferguson Lab (Pritzker School of Molecular Engineering), and most recently with the Vitelli Group at the James Franck Institute.

news

Aug 18, 2026 I’m starting my PhD in Data Science at UC San Diego (UCSD) this fall!
Jun 01, 2026 Graduated from the MPCS Master's Program in Computer Science at UChicago
Jun 01, 2025 I graduated from UChicago!

selected publications

  1. arXiv
    Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size
    Smayan Khanna, Doruk Efe Gökmen, Risi Kondor, and 1 more author
    Sep 2025
  2. JCIM
    FlowBack: A Generalized Flow-Matching Approach for Biomolecular Backmapping
    Mike Jones, Smayan Khanna, and Andrew Ferguson
    Journal of Chemical Information and Modeling, American Chemical Society (ACS), Jan 2025
  3. Biophys. J.
    Thermodynamics and kinetics of DNA and RNA dinucleotide hybridization to gaps and overhangs
    Brennan Ashwood, Michael S. Jones, Aleksandar Radakovic, and 6 more authors
    Biophysical Journal, Chicago, Jul 2023