Publications

Selected papers are listed first. Equal contribution is marked with *.

Selected Publications

TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models
Zeqing Wang*, Shiyuan Zhang*, Chengpei Tang, and Keze Wang.
CVPR 2026 DataMFM Workshop
arXiv Code
Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body
Zeqing Wang, Qingyang Ma, Wentao Wan, Haojie Li, Keze Wang, and Yonghong Tian.
CVPR 2025 Highlight CCF-A
arXiv Code
Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering
Zeqing Wang, Wentao Wan, Qiqing Lao, Runmeng Chen, Minjie Lang, Keze Wang, and Liang Lin.
IEEE Transactions on Multimedia CCF-A Q1
arXiv Code
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
Xinyu Wei, Kangrui Cen, Hongyang Wei, Zhen Guo, Bairui Li, Zeqing Wang, Jinrui Zhang, and Lei Zhang.
CVPR 2026 CCF-A
Project Page
Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation
Hui Fu, Zeqing Wang, Ke Gong, Keze Wang, Tianshui Chen, Haojie Li, Haifeng Zeng, and Wenxiong Kang.
AAAI 2024 CCF-A
Project Page Code

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
Shuang Liang, Zeqing Wang, Yuxian Li, Xihui Liu, and Han Wang.
preprint
arXiv
VideoVerse: How Far is Your T2V Generator from a World Model?
Zeqing Wang*, Xinyu Wei*, Bairui Li*, Zhen Guo, Jinrui Zhang, Hongyang Wei, Keze Wang, and Lei Zhang.
preprint
Homepage & Leaderboard
PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models
Zeqing Wang, Keze Wang, and Lei Zhang.
preprint
Code & Ckpt
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
Xinyu Wei, Jinrui Zhang, Zeqing Wang, Hongyang Wei, Zhen Guo, and Lei Zhang.
preprint
arXiv Code
A Novel College Entrance Filling Recommendation Algorithm Based on Score Line Prediction and Multi-feature Fusion
Zeqing Wang, Shengpeng Ji, Xin Li, Zixuan Zhao, Pengxu Wang, and Xiaosong Han.
Computer Science Chinese CCF-B
Paper Code
E3ID: An Efficient End to End Person Search Model
Siyang Wang, Yanchun Liang, Ao Li, Zeqing Wang, and Xiaosong Han.
Pattern Recognition Letters CCF-C Q2
Paper
A Continual Learning Paradigm for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks
Wentao Wan*, Nan Kang*, Zhuojie Yang, Zeqing Wang, Keze Wang, and Liang Lin.
preprint
arXiv