I am currently an Associate Professor and Ph.D. advisor in the School of Computer Science and Technology at Tongji University. Previously, I was a postdoctoral research associate at Shanghai Jiao Tong University and received the Ph.D. degree in Computer Science and Technology from Tongji University in 2022.

Research Interests

My research interests include explainable AI, computer vision, and AI safety.

Publications

• Multilingual Safety Alignment via Self-Distillation. arXiv preprint 2026
  Ruiyang Qin*, Qingzhuo Wang*, Dongrui Liu, Qiang Li, Zhihua Wei, Wen Shen† Download pdf

• A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions. ICML 2026
  Qingzhuo Wang*, Ruiyang Qin*, Zhenxin Qin, Wen Shen†, Zhihua Wei† Download pdf

• Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions. ICML 2026
  Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen† Download pdf

• Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement. ACL 2026
  Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen† Download pdf

• FOSK: Fast Open-Vocabulary 3D Instance Segmentation via Consensus-Filtered Knowledge Distillation. ICASSP 2026
  Hongrui Wu*, Zhicheng Gao*, Jin Cao, Kelu Yao, Wen Shen†, Zhihua Wei† Download pdf

• TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation. arXiv preprint 2026
  Qingzhuo Wang, Leilei Wen, Juntao Chen, Kunyu Peng, Ruiyang Qin, Zhihua Wei, Wen Shen† Download pdf

• Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift. arXiv preprint 2026
  Zhihua Wei*, Qiang Li*, Jian Ruan, Zhenxin Qin, Leilei Wen, Dongrui Liu, Wen Shen† Download pdf

• Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions. NeurIPS 2025
  Leilei Wen, Liwei Zheng, Hongda Li, Lijun Sun, Zhihua Wei, Wen Shen† Download pdf

• Leveraging Debiased Cross-modal Attention Maps and Code-based Reasoning for Zero-shot Referring Expression Comprehension. ICCV 2025
  Juntao Chen, Wen Shen†, Zhihua Wei†, Lijun Sun†, Hongyun Zhang Download pdf

• A Unified Approach to Interpreting Self-supervised Pre-training Methods for 3D Point Clouds via Interactions. CVPR 2025
  Qiang Li, Jian Ruan, Fanghao Wu, Yuchi Chen, Zhihua Wei†, Wen Shen† Download pdf

• Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing. IEEE TPAMI 2024
  Wen Shen, Zhihua Wei, Qihan Ren, Binbin Zhang, Shikun Huang, Jiaqi Fan, Quanshi Zhang† Download pdf

• Batch Normalization Is Blind to the First and Second Derivatives of the Loss. AAAI 2024
  Zhanpeng Zhou*, Wen Shen*, Huixin Chen*, Ling Tang, Yuefeng Chen, Quanshi Zhang† Download pdf

• Defects of Convolutional Decoder Networks in Frequency Representation. ICML 2023
  Ling Tang*, Wen Shen*, Zhanpeng Zhou, Yuefeng Chen, Quanshi Zhang† Download pdf

• Interpreting Representation Quality of DNNs for 3D Point Cloud Processing. NeurIPS 2021
  Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang† Download pdf

• Interpretable Compositional Convolutional Neural Networks. IJCAI 2021
  Wen Shen*, Zhihua Wei*, Shikun Huang, Binbin Zhang, Jiaqi Fan, Ping Zhao, Quanshi Zhang† Download pdf

• Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing. CVPR 2021
  Wen Shen*, Zhihua Wei*, Shikun Huang, Binbin Zhang, Panyue Chen, Ping Zhao, Quanshi Zhang† Download pdf

• 3D-Rotation-Equivariant Quaternion Neural Networks. ECCV 2020
  Wen Shen*, Binbin Zhang*, Shikun Huang*, Zhihua Wei, Quanshi Zhang† Download pdf