Zewei Deng

I am a Ph.D. student in Industrial and Systems Engineering at the University of Minnesota Twin Cities, advised by Prof. Liyan Xie. Since Summer 2026, I have also served as a Graduate Research Assistant.

Research

My research develops statistical, coding-theoretic, and optimization methods for trustworthy and robust learning systems. I work on LLM watermarking and provenance, distributionally robust inference under model misspecification, and uncertainty-aware sequential modeling.

Watermark integrity — detecting edits and localizing suspicious regions.
Watermarkability — measuring and improving compatibility with logit-based watermarks.
Sequential and robust learning — uncertainty-aware agentic simulation and inference for delayed point processes.

Before Minnesota, I earned an M.S. in Applied Data Science from the University of Chicago and a B.S. in Statistics from UIUC, with minors in Computer Science and Economics.

See my publications, research projects, or download my CV.

selected publications

Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting Codes

Zewei Deng, Muhammad Siddeek, Liyan Xie, and 4 more authors

In Findings of the Association for Computational Linguistics: EMNLP 2026, Oct 2026

Bib HTML PDF

@inproceedings{deng2026detecting,
  title = {Detecting Post-generation Edits to Watermarked {LLM} Outputs via Error-Correcting Codes},
  author = {Deng, Zewei and Siddeek, Muhammad and Xie, Liyan and Seif, Mohamed and Wang, Mengdi and Poor, H. Vincent and Goldsmith, Andrea},
  booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2026},
  month = oct,
  year = {2026},
  address = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  pages = {45788--45796},
}

Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks

Zewei Deng, Mohamed Seif, and Liyan Xie

2026

arXiv:2610.22810

arXiv Bib

@unpublished{deng2026watermarkability,
  title = {Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks},
  author = {Deng, Zewei and Seif, Mohamed and Xie, Liyan},
  note = {arXiv:2610.22810},
  year = {2026},
}

Distributionally Robust Inference for Delayed Point Processes

Zewei Deng, Shuyi Chen, Shixiang Zhu, and 1 more author

Working paper. Workshop version forthcoming at the INFORMS Data Mining and Decision Analytics Workshop , 2026

Extended manuscript in preparation for submission to the Annals of Applied Statistics (AOAS).

Bib

@unpublished{deng2026robust,
  title = {Distributionally Robust Inference for Delayed Point Processes},
  author = {Deng, Zewei and Chen, Shuyi and Zhu, Shixiang and Xie, Liyan},
  note = {Extended manuscript in preparation for submission to the Annals of Applied Statistics (AOAS).},
  year = {2026},
}