Haimeng Zhao

Haimeng Zhao

PhD Student in Physics

Caltech

Welcome!

Hello ~ I’m Haimeng Zhao /haɪ məŋ dʒaʊ/ (赵海萌), a PhD student in Physics at Caltech, advised by John Preskill and Hsin-Yuan Huang. I’m deeply fascinated by how the universe works and how we can possibly understand it. So I started working in the intersection of Physics and Intelligence.

In particular, I’m interested in the physical nature of learning and computation. Three overarching questions motivate my work:

  1. How do physical laws impact our ability to learn and how to harness them?
  2. How does our (in)ability to learn impact our perception of the physical reality?
  3. What is the ultimate physical limit of learning and computation?

I draw tools from theoretical physics, computer science, and machine learning to answer these questions.

I also worked as a Student Researcher at Google Quantum AI in 2025 Summer. Before Caltech, I received my Bachelor’s degree in Mathematics and Physics with Honours from Tsinghua University. I was an undergrad research fellow in John Preskill’s group at IQIM, Caltech and an exchange student in Giuseppe Carleo’s group at EPFL in Switzerland. At Tsinghua, I worked on quantum information in Dong-Ling Deng’s group at IIIS and AI for Astronomy with Wei Zhu.

Interests

  • Quantum Information, Algorithms, and Learning Theory
  • Quantum Many-body Physics
  • AI + Physics

Education

  • PhD Student in Physics

    Caltech

  • BS in Mathematics and Physics, 2024

    Tsinghua University

  • Outstanding Graduate, 2020

    Shanghai High School

Publications

(2025). Random Stinespring superchannel: converting channel queries into dilation isometry queries.

PDF

(2025). Entanglement-induced provable and robust quantum learning advantages. npj Quantum Information 11, 127.

PDF Code arXiv Talk

(2024). Learning quantum states and unitaries of bounded gate complexity. PRX Quantum, 5(4), 040306. Featured on the cover and in the International Year of Quantum Collection.

PDF Code arXiv Talk

(2024). Empirical Sample Complexity of Neural Network Mixed State Reconstruction. Quantum 8, 1358.

PDF Code arXiv

Contact