Kimia Shaban

PhD Student, Computer Science, University of Toronto.
Advised by Dr. Babak Taati. Faculty Affiliate, Vector Institute. Research Appointee, KITE UHN.

prof_pic_color.png

I am a PhD student in Computer Science at the University of Toronto, working on AI for healthcare and computer vision.

Before my PhD, I completed an MMath in Combinatorics & Optimization at the University of Waterloo, supervised by Dr. Karen Yeats. I also worked with Dr. Paul-Hermann Balduf on machine learning for Feynman period estimation; our joint work is published in the Journal of High Energy Physics. My master’s thesis is available here.

I grew up in Waterloo, Ontario. Outside of research, I enjoy playing piano, hiking with my dog, and playing Tetris.

news

Mar 02, 2026 New preprint: When Does RL Help Medical VLMs? — disentangling vision, SFT, and RL gains. Project page here.
Sep 01, 2025 Started my PhD in Computer Science at the University of Toronto, advised by Dr. Babak Taati. Also joined the Vector Institute as a Faculty Affiliate Researcher and KITE UHN as a Research Appointee.
May 01, 2025 Awarded the NSERC Canada Graduate Scholarship — Doctoral (CGS-D), $40,000/year for 2025–2028.

selected publications

  1. Preprint
    When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
    others and Kimia Shaban
    arXiv preprint, 2026
  2. JHEP
    Predicting Feynman periods in φ^4-theory
    Paul-Hermann Balduf and Kimia Shaban
    Journal of High Energy Physics, Nov 2024