Welcome to Wenjie’s Academic Pages

👤 About Me

Name        : Wenjie Zhu（朱文杰)
Position    : Ph.D. Candidate 
Affiliation : Department of Computing, Hong Kong Polytechnic University
Location    : Changsha, China
Languages   : Chinese (Native), English (Fluent)

I am a fourth year Ph.D student at the Visual Computing Lab, Hong Kong Polytechnic University, advised by IEEE Fellow Prof. Lei Zhang and IEEE Fellow VP. Wenjun Zeng. My research sits at the intersection of Machine Learning and Computer Vision, with a core mission of building Trustworthy AI Systems.

• 2022 – 2025: Focused on Model Reliability, specifically in Out-of-Distribution (OOD) detection and generalization for Vision-Language Models (VLMs).
• 2026 – Present: Transitioning toward AI Alignment and Safety, exploring how to ensure long-term value alignment and security through Continual Learning frameworks..

🎓 B.S. in [Software Engineering] — [Central South University], [2020]
🎓 M.S. in [Computing Engineering] — [New York University], [2022]
🎓 Ph.D. in [Computing] — [Hong Kong Polytechnic University], [2022 - Present]

🔬 Research Interests

🧠 OOD Detection & Test Time Adaptation

Research on enabling models to reliably detect inputs that fall outside the training distribution and maintain robust performance under distribution shifts at test time.

Keywords: OOD detection OOD generalization test time adaptation

🤖 AI Alignment & AI Safety

Research on ensuring large language models and autonomous agents pursue intended goals, remain controllable, and behave safely and reliably in alignment with human values across diverse deployment contexts.

Keywords: Alignment Safety

📊 Continual Learning

Research on enabling large language models and agents to continuously acquire new knowledge and skills over time without forgetting previously learned capabilities.

Keywords: Continual Learning

📄 Selected Publications

📌 Full list on Google Scholar

2026

• [ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning]
  Wenjie Zhu, Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang Computer Vision and Pattern Recognition (CVPR’26), 2026
  

2025

• [Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection]
  Wenjie Zhu, Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang the 34th ACM International Conference on Multimedia (ACMMM’25), 2025
  

2024

• [LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models]
  Yabin Zhang, Wenjie Zhu, Chenhang He, Lei Zhang European Conference on Computer Vision (ECCV’24), 2024
  

• [Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models]
  Yabin Zhang, Wenjie Zhu, Hui Tang, Zhiyuan Ma, Kaiyang Zhou, Lei Zhang Computer Vision and Pattern Recognition (CVPR’24), 2024

🏅 Academic Service

Reviewer / Program Committee

🏆 Honors & Awards