Kejia Zhang
Kejia Zhang

Master Student

Xiamen University

About Me

I am a second-year M.S. student in the Department of Artificial Intelligence at Xiamen University, fortunate to be advised byadvised by Prof. Zhiming Luo. Previously, I received a B.S. in Mathematics from Anhui University, where I work closely with Prof. Haifeng Zhang during my undergraduate studies.

My email: kejiaz171@gmail.com

Interests
  • Trustworthy LVMs
  • Computer Vision
  • Neural Network Robustness
Education
  • Department of Artificial Intelligence

    Xiamen University

  • School of Mathematical Sciences

    Anhui University

📚 My Research

My current research focuses on hallucinations in large multimodal models, with the goal of improving their trustworthiness and reliability. I also have prior experience in neural network robustness, particularly in adversarial training and adversarial attack methods.

📩 (AD) I am seeking a PhD position for Fall 2026, with a focus on Reliable LVMs and adversarial robustness. If you are aware of any opportunities that align with my research interests, please feel free to contact me. Thank you!

🏅 Honors & Awards
  • National Encouragement Scholarship, 2023
  • Natioanl Second Prize, Chinese Undergraduate Mathematical Contest in Modeling (CUMCM), 2022
  • Academic Technology Scholarship, 2021 & 2022
🌋 Special Thanks

I have had the pleasure of collaborating with and learning from the following institutions, where I experienced invaluable growth and joy:

Anhui University
Xiamen University
Westlake University
Alibaba
DAMO Academy
🚀 Featured Publications
🏖ī¸ Publications
(2025). Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs. Preprint.
(2024). Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment. Preprint.
(2024). A Collaborative Framework Using Multimodal Data and Adaptive Noise for Human Behavior Anomaly Detection. International Joint Conference on Neural Networks (IJCNN).
(2024). Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness. Preprint.
🗞ī¸ Recent News
----- Global Visitor Map -----