Mengyu Zhao

PhD in ECE, Rutgers University

mypic.jpg

CoRE Building, Room 735

96 Frelinghuysen Rd

Piscataway, NJ, 08854

Hi, I am Mengyu Zhao, a third-year PhD student in the Department of Electrical and Computer Engineering (ECE), Rutgers University, working with Prof. Shirin Jalali.

My research interests primarily focus on Inverse Problems, Image and Video Compression and Reconstruction, Efficient AI, etc.

  • Inverse Problem: Exploring theoretical performance limits and developing efficient, robust algorithms (e.g., generative models, implicit priors, NeRF, etc.) for imaging systems.
  • Efficient AI: Improving efficiency in vision-LLM

Before my PhD, I got Master’s in Statistics at Rutgers University and Bachelor’s degree from Xi’an Jiaotong University (XJTU), advised by Prof. Xiaohu Yang.

I am always open to discussions and collaborations—please feel free to reach out! This semester, I am organizing a reading group focusing on deep learning and inverse problems.

Outside of academia, I enjoy playing tennis and hiking. Let me know if you would like to meet up for a tennis rally!

Email: mengyu.zhao [at] rutgers [dot] edu

news

Dec 11, 2024 Present our work on UNN for snapshot compressive imaging in NeurIPS 2024, Vancouver, Canada
Sep 27, 2024 Invited as a reviewer of ICLR 2025.
Sep 26, 2024 One paper got accepted by NeurIPS 2024!
May 23, 2024 Presented our work of mask analysis for snapshot compressive imaging at Conference on Inverse Problems for Partial Differential Equations, Rutgers University.
Mar 25, 2024 Passed my qualifying exam. Thanks for my advisor’s help on my exam!

selected publications

  1. arXiv
    Saturation in Snapshot Compressive Imaging
    Mengyu Zhao, and Shirin Jalali
    Submitted, 2025
    arXiv
  2. arXiv
    Theoretical Characterization of Effect of Masks in Snapshot Compressive Imaging
    Mengyu Zhao, and Shirin Jalali
    Submitted (longer version of Allerton 2023 paper), 2025
    arXiv
  3. NeurIPS
    Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
    Mengyu Zhao, Xi Chen, Xin Yuan, and Shirin Jalali
    Advances in Neural Information Processing Systems, 2024
    arXiv Code
  4. Allerton
    Theoretical Analysis of Binary Masks in Snapshot Compressive Imaging Systems
    Mengyu Zhao, and Shirin Jalali
    2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2023
    arXiv