|
Wenjie Zhu My name is Wenjie Zhu, and I am a fourth-year Ph.D. candidate in the VC Lab at The Hong Kong Polytechnic University. I am fortunate to be advised by IEEE Fellow Prof. Lei Zhang and IEEE Fellow Prof. Wenjun Zeng. Before starting my Ph.D., I received my M.S. degree from New York University and my B.S. degree from Central South University. |
|
ResearchI'm interested in computer vision, machine learning, trustworthy AI, AI in Health. Some papers are highlighted. |
|
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
Wenjie Zhu, Yabin Zhang, Liang Xu, Xin Jin, Wenjun Zeng, Lei Zhang, ECCV, 2026 project page / arXiv we propose a novel framework named Dual Distribution Estimation (DDE), shifting the zero-shot NTTA paradigm from instance-level learning to training-free Gaussian distribution modeling. |
|
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, CVPR, 2026 (Oral) project page / arXiv we propose the ANTS approach by leveraging the understanding and reasoning capabilities of MLLMs. |
|
Knowledge Regularized Negative Feature Tuning of Vision-Language Models
Wenjie Zhu Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang, ACMMM, 2025 (Oral) project page / arXiv we propose a novel framework named Knowledge Reglarized Negative Feature Tuning (KR-NFT). |
|
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
Wenjie Zhu Yabin Zhang, Xin Jin, Wenjun Zeng, Lei Zhang, arXiv, 2026 arXiv MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models |
|
lapt: label-driven automated prompt tuning for ood detection with vision-language models
Yabin Zhang, Wenjie Zhu, Chenhang He, Lei Zhang, ECCV, 2024 bibtex we introduce Label-driven Automated Prompt Tuning (LAPT), a novel approach to OOD detection that reduces the need for manual prompt engineering. |
|
Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
Yabin Zhang, Wenjie Zhu, Hui Tang, Zhiyuan Ma, Chenhang He, Lei Zhang, CVPR, 2024 we introduce a versatile adaptation approach that can effectively work under all three settings. |
Miscellanea |
Academic Service |
Reviewer, Neurips 2026
Reviewer, ECCV 2026 Reviewer, ICML 2026 Reviewer, AAAI 2026 Reviewer, ACMMM 2025 Reviewer, ICLR 2025 Reviewer, ECCV 2024 Reviewer, CVPR 2024 |
|
Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page. |