Vinod Raman

Vinod Raman

Research Scientist @ Google DeepMind

I'm a Research Scientist at Google DeepMind, improving Gemini's fundamental capabilities for retrieval.

I completed my Ph.D. in Statistics at the University of Michigan in 2025, where I was fortunate to be advised by Ambuj Tewari. My Ph.D. was graciously supported by the 2022 National Science Foundation Graduate Research Fellowship (NSF GRFP) and the 2025 Apple Scholars in AI/ML PhD Fellowship. Prior to my Ph.D, I double-majored in Computer Science and Chemical Engineering and worked with Mahdi Cheraghchi, Sindhu Kutty, and Andrej Lenert.

My research interests lie in the foundations of machine learning. During my Ph.D, I worked on various topics in learning theory, including online learning, adversarial robustness, differential privacy, and language generation. Currently, I work on reinforcement learning for large language models.

Fun facts about me:

  1. I love Thai food and have been to more than 40 Thai restaurants across the US.
  2. I love horror movies and horror books.
  3. I've always wanted to be a professional bodybuilder.
Post-training RL for LLMs Online Learning Differential Privacy Learning Theory
01

In Submission

02

Publications

2026
2025
2024
2023
2022
2019
  • 1
    Design of thermophotovoltaics for tolerance of parasitic absorption with Tobias Burger, Andrej Lenert Optics Express, 2019
    PDF
03

Preprints