个人信息
Personal Information
联系方式
Contact Information
个人简介
Personal Profile
沈雯,同济大学计算机科学与技术学院副教授,博士生导师,入选“2024年上海市晨光计划”。主要研究方向为深度学习及其可解释性与安全性等。她在TPAMI、ICML、NeurIPS、CVPR、AAAI、IJCAI等国际顶级会议和期刊上发表论文二十余篇,其中一项代表性工作被人工智能学会推荐A类会议CVPR评选为亮点成果(Highlight);主持国自然面上项目、国自然青年科学基金(C类)项目、上海市新一代信息技术青年计划项目等。
申请人所在的同济大学智能信息处理实验室在团队带头人苗夺谦教授(IRSS Fellow、CAAI Fellow)带领下,多年来一直从事人工智能、机器学习、文本与图像理解等理论研究,先后主持国家自然科学基金 20 余项, 国家重点研发计划项目(课题) 2 项,军委科技委项目 1 项,公安部重大专项 1 项,上海市项目 5 项。
上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg【代表性论文,仅展示可解释性和安全性方向】
符号“*”表示通讯作者,符号“#”表示共同一作。
[1] Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen*. Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement, Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), San Diego, California, July 2, 2026. (CCF-A类, accepted)
[2] Leilei Wen, Liwei Zheng, Hongda Li, Lijun Sun, Zhihua Wei, Wen Shen*. Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions, Proceedings of Advances in Neural Information Processing Systems (NeurIPS), San Diego, CA, December 2, 2025. (CCF-A类)
[3] Qiang Li, Jian Ruan, Fanghao Wu, Yuchi Chen, Zhihua Wei*, Wen Shen*. A Unified Approach to Interpreting Self-supervised Pre-training Methods for 3D Point Clouds via Interactions, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, Tennessee, USA, June 11, 2025. (CCF-A类)
[4] Wen Shen#, Zhihua Wei#, QihanRen, Binbin Zhang, Shikun Huang, Jiaqi Fan, and Quanshi Zhang*; Interpretable Rotation-EquivariantQuaternion Neural Networks for 3D Point Cloud Processing, IEEE Transactions on Pattern Analysis and MachineIntelligence (IEEE T-PAMI), vol. 46, no. 5, pp. 3290-3304, January 8, 2024. (CCF-A类, IF=24.314)
[5] Wen Shen, Qihan Ren, Dongrui Liu, and QuanshiZhang*. Interpreting Representation Qualityof DNNs for 3D Point Cloud Processing, Proceedingsof Advances in Neural Information Processing Systems (NeurIPS), Virtual,December 6, 2021. (CCF-A类)
[6] Wen Shen#, Zhihua Wei#, Shikun Huang, Binbin Zhang, Panyue Chen,Ping Zhao, and Quanshi Zhang*. Verifiability andPredictability: Interpreting Utilities of Network Architectures for 3D PointCloud Processing, Proceedings of the IEEE/CVF Conference on ComputerVision and Pattern Recognition (CVPR), Virtual, June 19, 2021. (CCF-A类)
[7] Wen Shen#, Zhihua Wei#, Shikun Huang, Binbin Zhang, Jiaqi Fan,Ping Zhao, and Quanshi Zhang*. InterpretableCompositional Convolutional Neural Networks, Proceedings ofInternational Joint Conference on Artificial Intelligence (IJCAI), Virtual, August23, 2021 (CCF-A类)
[8] Wen Shen, ZhihuaWei*, Qianwen Li, Hongyun Zhang, Duoqian Miao. Three-WayDecisions Based Blocking Reduction Models in Hierarchical Classification,Information Sciences, vol. 523, no. 2020, pp. 63-76, February 10, 2020. (JCR1区)
[9] Ling Tang#, Wen Shen#, Zhanpeng Zhou, Yuefeng Chen and Quanshi Zhang*; Defectsof Convolutional Decoder Networks in Frequency Representation, Fortieth International Conference on MachineLearning (ICML), Hawai, July 23, 2023 (CCF-A类)
[10] Zhanpeng Zhou#, WenShen#, Huixin Chen, Ling Tang, Yuefeng Chenand Quanshi Zhang*; BatchNormalization Is Blind to the First and Second Derivatives of the Loss, Thirty-Eighth AAAI Conference on ArtificialIntelligence (AAAI-24), Vancouver, February 20, 2024 (CCF-A类)
[11] Wen Shen#, Binbin Zhang#, Shikun Huang#,Zhihua Wei, and Quanshi Zhang*. 3D-Rotation-EquivariantQuaternion Neural Networks, Proceedings of European Conference onComputer Vision, Virtual (ECCV), August 23, 2020. (CCF-B类)

文件上传中...