Me
Zhenxin Ai
Incoming Ph.D. Student, HKUST(GZ)
aikunkun34 [at] gmail [dot] com

About

I will soon pursue my Ph.D. at the Hong Kong University of Science and Technology (Guangzhou), advised by Assistant Prof. Haiyun He. I received my B.Eng. in Artificial Intelligence from Jiangxi University of Science and Technology, where I was advised by Prof. Huilan Luo. During my senior year, I was a visiting student at Westlake University, working with Assistant Prof. Huan Wang. My research interests include watermarking for multimodal large language models and world models. I am always open to related collaborations. If you are interested in discussing potential projects, please feel free to contact me via email. I will be attending ISIT 2026 and ICML 2026, and I look forward to meeting you in person there.

Interests

  • Multi-modal Large Language Models
  • Watermarking for LLMs
  • World Models
  • Computer Vision

Education

Jiangxi University of Science and Technology
  • B.Eng. in Artificial Intelligence, Sep. 2021 - Jun. 2025
  • Advisor: Prof. Huilan Luo

News

  • [ICML'26] PASA was accepted by ICML 2026.
  • [TCSVT] Niagara was accepted by TCSVT.
  • [HKUST(GZ)] Joined HKUST(GZ) as a Research Assistant.
  • [JXUST] Graduated from Jiangxi University of Science and Technology with a B.Eng. in Artificial Intelligence.
  • [TGRS] LiteSalNet was accepted by TGRS.

Experiences

Aug. 2025 - Now
Research Assistant @ Hong Kong University of Science and Technology (Guangzhou)
Supervisor: Assistant Prof. Haiyun He
Feb. 2025 - Jul. 2025
Algorithm Intern @ Z.AI
Focus: Large Language Model Inference and Hallucination
Jul. 2024 - Jan. 2025
Visiting Student @ Westlake University
Supervisor: Assistant Prof. Huan Wang
Sep. 2021 - Jun. 2025
B.Eng. in Artificial Intelligence @ Jiangxi University of Science and Technology
Supervisor: Prof. Huilan Luo

Publications

PASA
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Zhenxin Ai, Haiyun He
ICML 2026
Paper Page Code
Niagara
Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View
Xianzu Wu*, Zhenxin Ai*, Harry Yang, Ser-Nam Lim, Jun Liu, Huan Wang
TCSVT 2025
Paper Page Code
LiteSalNet
A Lightweight Multi-Stream Framework for Salient Object Detection in Optical Remote Sensing
Zhenxin Ai, Huilan Luo, Jianqin Wang
TGRS 2025
Paper Page Code

GitHub

Official implementation of PASA: A principled embedding-space watermarking approach for LLM-generated text under semantic-invariant attacks.
Python
Star   – Fork   –
Official PyTorch implementation of Niagara: Normal-Integrated Geometric Affine Field for Single-View Scene Reconstruction.
Python
Star   – Fork   –
A PyTorch implementation of LiteSalNet for Remote Sensing Salient Object Detection.
Python
Star   – Fork   –

Selected Honors & Awards

  • Coming Soon...

Academic Services

  • Coming Soon...