中科大先研院研究生校内导师简历

庄连生 工学博士/副教授

姓名 庄连生
学位/职称 工学博士/副教授
所属单位 网络空间安全学院
办公室电话
Email lszhuang@ustc.edu.cn
教育背景
2001.9-2006.7 中国科学技术大学,博士(硕博)
1997.9-2001.7 中国科学技术大学,本科
研究领域
课题组主要从事计算机视觉、自然语言处理、认知科学等领域的交叉研究,感兴趣的研究方向包括:

(1) 多模态认知计算:主要研究多模态大模型及其推理技术,重点关注其在医疗健康领域、网络空间安全领域的应用;

(2) 多智能体对抗决策:主要研究强化学习和机器博弈,重点关注其在游戏AI、网络空间安全领域的应用。

希望招收对上述方向感兴趣的研究生,尤其欢迎有相关研究经历的研究生。
任职经历
2011.2-2011.11,微软亚洲研究院,访问研究员(”铸星计划“入选者)
2012.2-2013.2,加州大学伯克利分校,访问学者(中科院公派)
2016.2-2017.2,加州大学伯克利分校,访问学者(国家留学基金委)
获得荣誉、奖项
1. 2023年安徽省教学成果一等奖,1/1, 2024年;
主持、参与项目
1. 国家自然科学基金企业联合重点项目,“知识和数据共同驱动的小样本目标识别理论和方法”,2021.1-2024.12;(主持)
2. 科技部科技创新2030——“新一代人工智能”重大项目,2019.12-2022.12;(子课题主持)
3. 国家自然科学基金面上项目,“面向非完备信息机器博弈的知识驱动深度强化学习方法研究”,2020.1-2023.12;(主持)
4. 国家自然科学基金面上项目,“复杂场景下非合作目标鲁棒识别方法研究”,2015.1-2018.12;(主持)
5. 国家自然科学基金青年项目,“基于稀疏表示的高效鲁棒大规模物体识别方法研究”,2012.1-2014.12;(主持)
论文、著作、成果
近几年代表性论文:
1. Aodi Li, Liansheng Zhuang, Xiao Long, Minghong Yao, Shafei Wang, "Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes",   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'25), June 11-15, Nashville TN, USA, 2025; (CCF-A类会议,通讯作者)
2. Xiao Long, Liansheng Zhuang, Aodi Li, Minghong Yao, Shafei Wang, "EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering", The 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25), Feb, 2025;  (CCF-A类会议,通讯作者)
3. Zhengdao Shao, Liansheng Zhuang, Yihong Huang, Houqiang Li, Shafei Wang, "Purified Policy Space Response Oracles for Symmetric Zero-Sum Games",  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), August, 2024; (CCF-B类期刊,通讯作者, IF:10.2)
4. Xiao Long, Liansheng Zhuang, Aodi, Li, Houqiang Li, Shafei Wang, "Fact Embedding through Diffusion Model for Knowledge Graph Completion",  The 2024 ACM Web Conference (WWW'24), 2024; (CCF-A类会议,通讯作者)
5. Yukun Zuo, Hantao Yao, Liansheng Zhuang, Changshegn Xu, "Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), pp.1-15, 12 April 2024; (CCF-A类期刊, IF:20.8)
6. Minghong Yao, Liansheng Zhuang, Houqiang Li, Jiuchang Wei, "Learning Label Dependencies for Visual Information Extraction", International Joint Conference on Artificial Intelligence (IJCAI-24), 2024;   (CCF-A类会议,通讯作者)
7. Xiao Long, Liansheng Zhuang, Aodi Li, Jiuchang Wei, Houqiang Li, Shafei Wang, "KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding", Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), 2024; (CCF-A类会议,通讯作者)
8. Minghong Yao, Zhiguang Liu, Liansheng Zhuang, Liangwei Wang, Houqiang Li, "A Robust Framework for One-shot Key Information Extraction via Deep Partial Graph Matching", IEEE Transactions on Image Processing (TIP), Vol.33, pp.1070-1079, 29 January 2024; (CCF-A类期刊,通讯作者,IF:10.8)
9. Shang Chai, Liansheng Zhuang, Fengying Yan, Zihan Zhou, "Two-stage Content-Aware Layout Generation for Poster Designs", The 31st ACM International Conference on Multimedia(MM'23), Ottawa, ON, Canada, Oct.29-Nov.3, 2023:8415-8423; (CCF-A类会议,通讯作者)
10. Junshan Hu, Liansheng Zhuang, Weisong Dong, Shiming Ge, Shafei Wang, "Learning Generalized Representation for Open Set Temporal Action Localization", The 31st ACM International Conference on Multimedia(MM'23), Ottawa, ON, Canada, Oct.29-Nov.3, 2023:1987-1996; (CCF-A类会议,通讯作者)
11. Shang Chai, Liansheng Zhuang, Fengying Yan, "LayoutDM: Transformer-based Diffusion Model for Conditional Layout Generation", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'23), Vancouver, BC, Canada, June 17-24, 2023:18349-18358; (CCF-A类会议,通讯作者)


更多论文请访问个人主页 http://staff.ustc.edu.cn/~lszhuang

编辑:徐若兰 2025-03-30 00:09:53