Yepeng Liu

yepengliu@ucsb.edu

Santa Barbara, California, USA

YL

About

Hi, I'm Yepeng. I'm currently a third-year Ph.D. student in Computer Science at the University of California, Santa Barbara. I'm very fortunate to be advised by Prof. Yuheng Bu. My current research mainly focuses on improving the safety, robustness, and reliability of AI models towards their deployment in the real world, especially watermarking Large Generative Models. Should you be interested in my research or wish to explore collaboration opportunities, please don't hesitate to drop me an email!

Selected Research

ConvexBench: Can LLMs Recognize Convex Functions?

Yepeng Liu, Yu Huang, Yu-Xiang Wang, Yingbin Liang, Yuheng Bu

ICML 2026

[paper][code will be released soon]

In-Context Watermarks for Large Language Models

Yepeng Liu, Xuandong Zhao, Christopher Kruegel, Dawn Song, Yuheng Bu

ICLR 2026

[paper][code]

Image Watermarks are Removable Using Controllable Regeneration from Clean Noise

Yepeng Liu,Yiren Song,Hai Ci,Yu Zhang,Haofan Wang,Mike Zheng Shou,Yuheng Bu

ICLR 2025

[paper][code]

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach

Haiyun He^, Yepeng Liu^, Ziqiao Wang, Yongyi Mao, Yuheng Bu

NeurIPS 2025

[paper][code]

Adaptive Text Watermark for Large Language Models

Yepeng Liu, Yuheng Bu

ICML 2024

[paper][code]

Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs

Yepeng Liu, Xuandong Zhao, Dawn Song, Yuheng Bu

arXiv 2025

[paper][code will be released soon]

Position: LLM Watermarking Should Align Stakeholders’ Incentives for Practical Adoption

Yepeng Liu, Xuandong Zhao, Dawn Song, Gregory W. Wornell, Yuheng Bu

ACL Findings 2026

[paper]

Services

NeurIPS(24',25'), ICLR(24',25'), ICML(25'), AAAI(25'), AISTATS(24')