Hanqian Li(李翰乾)

Hanqian Li(李翰乾)

M.Phil student @ HKUST(GZ)

About me

Hi!👋 My name is Hanqian Li (李翰乾). I am currently an M.Phil student in the AI Thrust, Information Hub at the HKUST(GZ), supervised by Prof. Xuming Hu and Prof. Hui Xiong(AAAS, AAAI, IEEE Fellow). Previously, I received my B.Eng. degree from Shandong University (SDU), supervised by Prof. Jinglin Zhang.

My research interests include:

  • Watermarking for generative models, including watermark for LLMs and diffusion models.
  • Enhancing reasoning ability of LLMs, including MLLMs.

I am honored to collaborate with Dr. Aiwei Liu, Dr. Sirui Huang, and Jungang Li on research projects. I am happy to chat and collaborate on research. Feel free to contact me at my email.

🔥 News

  • [2026.08] Three papers have been accepted at EMNLP 2026. 🎉
  • [2025.06] I have graduated from Shandong University, majoring in Automation Engineering. 🎓
  • [2025.04] A paper on enhancing LLMs for structured knowledge has been accepted at SIGIR 2025.

📕 Publications

HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge
HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge

Sirui Huang*, Hanqian Li*, Yanggan Gu, Xuming Hu, Qing Li, Guandong Xu

SIGIR 2025

[Paper] [Code]

Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes
Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes

Chen Ling*, Tongwei Zhang*, Hanqian Li*, Nai Ding†

EMNLP 2026

[Paper]

Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes
Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning

Chen Ling*, Hanqian Li*, Dongnan Liu, Keyu Qian, Jungang Li, Shiyi Wang, Xin Dong, Pengcheng Zhu, Wei Zhou, Linjian Mo, Nai Ding†

arXiv preprint. 2608.06938

[Paper]

VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Models
VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Models

Hanqian Li*, Aiwei Liu*†, Jungang Li*, Yu Huang, Shuliang Liu, Qi Zheng, Junhao Chen, Xuming Hu†

arXiv preprint. 2504.16359

[Paper] [Code]

RTV-Bench Visualization
$\mathcal{RTV}\text{-}Bench$: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through $\mathcal{R}$eal-$\mathcal{T}$ime $\mathcal{V}$ideo

Shuhang Xun, Sicheng Tao, Jungang Li, Yibo Shi, Zhixin Lin, Zhanhui Zhu, Yibo Yan, Hanqian Li, Linghao Zhang, Shikang Wang, Yixin Liu, Hanbo Zhang, Ying Ma, Xuming Hu

NeurIPS 2025

[Paper] [Code]

A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model
A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model

Qi Zheng, Shuliang Liu, Yu Huang, Sihang Jia, Jungang Li, Lyuhao Chen, Junhao Chen, Hanqian Li, Aiwei Liu, Yibo Yan, Xuming Hu

CVPR 2026

[Paper]

📖 Educations

  • 2025.08 - present, M.Phil Student, HKUST (GZ)
  • 2021.09 - 2025.06, B.Eng. in Automation, Shandong University

🖥️ Internship

  • 2025.10 - present, Research Intern, Ant Group
    Supervisor: Mr. Wei Zhou(Principal Researcher)
  • 2024.02 - 2025.06, Research Intern, HKUST (GZ)
    Supervisor: Prof. Xuming Hu

📝 Reviewing Services

  • Conferences: ICME, AAAI, NeurIPS, AAAI (2025 Workshop on PDLM)
  • Journals: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)