Vashisth Tiwari

Hi! 👋

I’m a PhD student at Carnegie Mellon University’s LTI, advised by Emma Strubell and Zico Kolter. Previously, I completed my master’s at CMU and a bachelor’s in Physics and Mathematics at the University of Rochester.

I’m broadly interested in bringing some formalism and better understanding to how and why LLM training methods work, and in improving the efficiency of LLMs (through better data and improved training dynamics). My work so far has focused on distillation and reinforcement learning during post-training.

I’ve been fortunate to learn from wonderful mentors: Oleksii and Adi at Nvidia (summer 2026), Giulia DeSalvo at DeepMind (summer 2025), and Beidi Chen, Lucio Dery, Clara Na at CMU.

---

---