博士，硕士生导师，助理研究员/师资博士后
电子邮件：zefanzhang@ccnu.edu.cn
【 教育经历 】
2023.9–2026.6 吉林大学 计算机科学与技术学院 计算机应用技术 博士
2020.9–2023.6 苏州大学 计算机科学与技术学院 计算机技术 硕士
2016.9-2020.6 浙江工业大学 计算机科学与技术学院 计算机科学与技术 学士
【 工作经历 】
2026.06 至今 华中师范大学 国家数字化工程技术研究中心 助理研究员
2022.11-2023.02 微软亚洲研究院（MSRA） 北京 多媒体计算组 实习
【 研究方向 】
多模态学习、多模态大模型、自然语言处理、教育智能体评估
【 科研项目 】
1.多模态认知计算技术研究及生物医药应用，20240601039RC，吉林省中青年科技创新卓越人才（团队）项目，2024.01-2025.12，在研，参与。
2.多模态骨关节影像智能计算方法研究，U21A20390，国家自然科学基金重点项目子项目，2022.01-2025.12，在研，参与。
3.面向肿瘤早期诊断的多模态数据语义关联挖掘研究，62576149，国家自然科学基金委员会，面上项目，2026.01-2029.12，在研，参与。
【 论文 】
1.Zhang Zefan, Zhang Weiqi, Li Yanhui, Bai Tian, Caption-aware multimodal relation extraction with mutual information maximization, Proceedings of the 32nd ACM International Conference on Multimedia (202410, CCF-A类会议，DOI: 10.1145/3664647.3681219)
2.Zhang Zefan, Zhang Weiqi, Li Yanhui, Bai Tian, Prototype-guided multimodal relation extraction based on entity attributes, Proceedings of the AAAI Conference on Artificial Intelligence, 39, 24, 26003-26011 (202504, CCF-A类会议，DOI: 10.1609/aaai.v39i24.34795)
3.Zhang Zefan, Zhang Weiqi, Suo Kailong, Li Yanhui, Bai Tian, Video-Level Multimodal Relation Extraction with Event-Entity Semantic Consistency, Proceedings of the 33rd ACM International Conference on Multimedia (202510, CCF-A类会议，DOI: 10.1145/3746027.3755557)
4.Zhang Zefan, Li Yanhui, Zhao Ruihong, Bai Tian, DAMON: Difference-Aware Medical Visual Question Answering via Multimodal Large Language Model, IEEE Journal of Biomedical and Health Informatics (202602, 中科院一区TOP, IF: 6.8，DOI: 10.1109/JBHI.2026.3663420)
5.Zhang Zefan, Zhang Xumeng, Jiang Shijie, Bai Tian, CogECI: Context Grounded Document-level Event Causality Identification via Large Language Models[J]. Knowledge-Based Systems, 2026. （中科院1区TOP， IF=7.6）
6.Zhang Zefan, Li Yanhui, Zhang Weiqi, Bai Tian, Dual-level dynamic heterogeneous graph network for video question answering, Neural Networks (202602, CCF-B类期刊, 中科院二区TOP, IF 6.5, DOI: 10.1016/j.neunet.2025.108094)
7.Zhang Zefan, Li Yanhui, Zhang Weiqi, Bai Tian, Prompting visual dialog with implicit logical knowledge, Knowledge and Information Systems, 67, 6, 4949-4966 (202503, CCF-B类期刊, IF 3.2, DOI: 10.1007/s10115-025-02384-8)
8.Jiang Tianling*, Zhang Zefan*, Li Xin, Ji Yi, Liu Chunping, Multi-view semantic understanding for visual dialog, Knowledge-Based Systems, 268, 110427 (202311, 共同一作，中科院一区TOP, IF 7.6, DOI: 10.1016/j.knosys.2023.110427)
9.Zhang Zefan, Li Shun, Ji Yi, Liu Chunping, Infer unseen from seen: Relation regularized zero-shot visual dialog, Journal of Visual Communication and Image Representation, 97, 103961 (202312, CCF-C类期刊, IF 2.6, DOI: 10.1016/j.jvcir.2023.103961)
10.Zhang Zefan, Jiang Tianling, Liu Chunping, Ji Yi, Coupling Attention and Convolution for Heuristic Network in Visual Dialog, 2022 IEEE International Conference on Image Processing (ICIP) (202210, CCF-C类会议，DOI: 10.1109/ICIP46576.2022.9898003)
11.Zhang Zefan, Jiang Tianling, Liu Chunping, Ji Yi, Multi-aware coreference relation network for visual dialog, International Journal of Multimedia Information Retrieval, 11, 4, 567-576 (202211, IF 3.8, DOI: 10.1007/s13735-022-00257-2)
12.Zhang Zefan, Ji Yi, Liu Chunping, Knowledge-aware causal inference network for visual dialog, Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (202306, CCF-B类会议，DOI: doi/abs/10.1145/3591106.3592272)
13. Sun Shengkai, Cheng Zhiyong, Zhang Zefan, Dong Jianfeng, Wang Meng, Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition, Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition (2026, CCF-A类会议)
14.Sun Shengkai, Zhang Zefan, Dong Jianfeng, Cheng Zhiyong, Chang Xiaojun, Wang Meng, Towards Efficient General Feature Prediction in Masked Skeleton Modeling, Proceedings of the IEEE/CVF International Conference on Computer Vision (2025, CCF-A类会议)
15.Gao Haiyan, Shi Dibo, Jiang Tianling, Li Xin, Zhang Zefan, Ji Yi, Li Ying, Liu Chunping, Scene graph generation with award-punishment strategy, Knowledge-Based Systems, 251, 109239 (202210, 中科院一区TOP, IF 7.6, DOI: 10.1016/j.knosys.2022.109239)
16.Lu Hongyuan, Li Zixuan, Zhang Zefan, Lam Wai, SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (202511, CCF-B类会议，DOI: 10.18653/v1/2025.emnlp-main.46)
17.Lu Hongyuan, Li Zixuan, Zhang Zefan, et al. Adam’s Law: Textual Frequency Law on Large Language Models[C]//Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026: 4079-4105. (CCF-A类会议)
18.Bai Tian, Li Chu, Peng Xinyue, Guan Haotian, Zhang Zefan, Wang Guishen, A novel drug-drug interaction prediction model based on line subgraph generation strategy, 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (202312, CCF-B类会议，DOI: 10.1109/BIBM58861.2023.10385887)
19.An Huilin, Zhang Zefan, Jiang Shijie, et al. TDP-DETR: Temporal dynamics perception framework for video moment retrieval and highlight detection[J]. Neural Networks, 2026: 109063. (CCF-B类期刊, 中科院二区TOP, IF 6.5)
20.Li Shun, Zhang Zefan, Ji Yi, Li Ying, Liu Chunping, Spatio-temporal graph-based semantic compositional network for video captioning, 2022 International Joint Conference on Neural Networks (IJCNN) (202207, CCF-C类会议，10.1109/IJCNN55064.2022.9892438)
【 招生要求 】
欢迎优秀的计算机相关的大二、大三本科生以及硕士生加入。
