I am a Master’s student at Nanjing University of Science and Technology. My research interests focus on the safety and interpretability of large foundation models, including large language models and text-to-image diffusion models. I work on neuron- and path-level analysis to understand and mitigate harmful generation, with recent research on path-level intervention and cultural bias in generative models. My work has appeared as preprints on arXiv.
📝 Publications
Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
Chuancheng Shi, Shangze Li, Shiming Guo, Simiao Xie, Wenhua Wu, Jingtong Dou, Chao Wu, Canran Xiao, Cong Wang, Zifeng Cheng, Fei Shen, Tat-Seng Chua
TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
Chuancheng Shi, Shangze Li, Wenjun Lu, Wenhua Wu, Cong Wang, Zifeng Cheng, Fei Shen, Tat-Seng Chua
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
Shaotian Li, Shangze Li, Chuancheng Shi, Wenhua Wu, Yanqiu Wu, Xiaohan Yu, Fei Shen, Tat-Seng Chua
📖 Education
- 2025.09 - 2028.06 (now), M.S. Student,NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY
- 2021.09 - 2025.06, Undergraduate Student, HENAN UNIVERSITY