Zihao Zhao
About Me
I am a first-year Computer Science Ph.D. student at the Center for Language and Speech Processing at Johns Hopkins University, where I am fortunate to be co-advised by Anjalie Field and Yinzhi Cao.
My research develops algorithms and systems for trustworthy AI, focusing on the safety, privacy, and alignment of large language and vision models. I am particularly interested in improving alignment while minimizing utility loss, through reasoning-based and post-training methods. I also work on establishing theoretical guarantees for the privacy and safety of AI systems deployed in sensitive domains such as healthcare.
Previously, I completed my undergraduate studies at Johns Hopkins University with a double major in Computer Science and Applied Mathematics, and a minor in Psychology.
I’m always happy to collaborate! If you’re interested in working together, feel free to reach out to me at zzhao71[at]jhu.edu.
News
- [09/2025] Our paper “Controlled Generation for Private Synthetic Text” has been accepted to EMNLP 2025! Check out the paper and the code repository.
Publications
-
EMNLP
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. -
EMNLP Demo
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. -
EMNLP Findings
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
Services
Conference Reviewers
Teaching
I was a teaching assistant for the following courses:
- Time Series Analysis (Spring 2024, Spring 2025)
Powered by Jekyll and Minimal Light theme.