Kia Ghods

cs + math @ princeton

prof_pic.jpg
kia.ghods [at] princeton (dot) edu

I am a second-year undergraduate at Princeton University , studying cs + math. I am broadly interested in the intersection of machine learning, mathematics, and cognitive science.

I am a researcher in Princeton’s Princeton Language and Intelligence Initiative , where I work on mechanistic interpretability and alignment of large language models and vision-language models. I am advised by Professors Jon Cohen and Tom Griffiths .

At Princeton, I am President of Princeton’s ACM chapter, Officer of AI@Princeton, and a member/co-organizer of various machine learning related reading groups. I previously interned at Hillspire and have worked at early-stage startups (i.e., Astralis).

Outside of academics, I am an avid fan of both playing and watching basketball and tennis. I also enjoy reading and writing.

You can reach me at [x] at princeton dot edu where [x] = kia.ghods.

latest posts

selected publications

  1. Interpretability
    vlmbinding.webp
    Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
    Declan Campbell, Sunayana Rane, Tyler Giallanza, Nicolò De Sabbata, Kia Ghods, Amogh Joshi, Alexander Ku, Steven M. Frankland, Thomas L. Griffiths^, Jonathan D. Cohen^, and Taylor Webb^
    NeurIPS, 2024
  2. Modeling
    mbe_figure.jpg
    Modeling the interplay between albumin-globulin metabolism and HIV infection
    Vivek Sreejithkumar, Kia Ghods, Tharusha Bandara, Maia Martcheva, and Necibe Tuncer
    Mathematical Biosciences and Engineering, 2023