Hi!

UCLA BAIR. NeuroAI. Etc.

prof_pic.jpg

Hi! I’m Saarang. I completed my PhD at UCLA in May 2026, advised by Dr. William Speier, where I used deep learning to better understand the brain (and sometimes vice versa). I’m now joining Google DeepMind, working on open-source medical AI.

cv · scholar · email

research focus

At UCLA, I focused on three main questions:

  1. Can we develop a foundation model for EEG that is useful for clinical applications?
  2. Can we uncover how seizures are modulated?
  3. Can we use deep learning to identify biomarkers and guide epilepsy treatment protocols?

current work

I’m also interested in more fundamental neuroscience questions, like “how does the brain process information?” During my PhD, I spent six months in London interning with the BrainAI team at Meta FAIR, where I worked on new approaches to this problem (paper coming soon!).

selected publications

  1. Uncovering spatiotemporal dynamics of the corticothalamic network at ictal onset
    Saarang Panchavati, Atsuro Daida, Benjamin Edmonds, and 8 more authors
    Epilepsia, 2024
  2. Distinct Spectral and Directional Thalamocortical Network Dynamics Define Focal Seizure Evolution
    Saarang Panchavati, Atsuro Daida, Sotaro Kanai, and 8 more authors
    medRxiv, 2026
  3. Laya: A LeJEPA approach to EEG via latent prediction over reconstruction
    Saarang Panchavati, Uddhav Panchavati, Hiroki Nariai, and 2 more authors
    arXiv preprint arXiv:2603.16281, 2026

news

  • Mar 2025 Started an internship with the BrainAI team at FAIR!

about me

I’m also a struggling Arsenal fan (is this our year???????), and I like composing for piano, singing Indian classical music, taking pictures of plants (@plantchavati), and training for more half marathons. If I wasn’t doing this, I’d probably study history (current favorite podcast).