Chirayu Nimonkar
Princeton Computer Science '26
Hey! I'm Chirayu, a senior studying computer science at Princeton with minors in Applied & Computational Mathematics and Statistics & Machine Learning.
I'm most interested in reinforcement learning, particularly the goal-conditioned and multi-agent settings. I want to answer: how do we build AI systems that discover and leverage universal principles the way humans do?
Previously I've worked at the intersection of cognitive science and ML, on ultra-low-field MRIs, and on building anatomically accurate brain and head models.
Selected Publications
Emergent Compositional Skills in Mixture-of-Experts VLAs
Workshop on Compositional Learning, ICML 2026
Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
arXiv preprint, 2025
Development of Anatomically Accurate Brain Model of Small Animals for Experimental Verification of Transcranial Magnetic Stimulation
IEEE Transactions on Magnetics, 2022
Patent: Anatomically Accurate Rodent Head Models and Brain Phantoms and Methods for Making and Using the Same
US Patent WO2023278864A1, 2023
Projects
Goal-Conditioned Multi-Agent RL
Self-supervised goal-reaching results in multi-agent cooperation and exploration.
work
Probing LLM Numeracy
Modeling low-dimensional internal representations of numbers in large language models.
work
Rat Brain Phantom
Anatomically accurate brain models of small animals for verifying transcranial magnetic stimulation.
work