About
I am a first-year PhD student in the IoT Thrust at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Zhiqing Hong. I obtained an MSc degree in Computer Science from the University of Copenhagen, where I was advised by Prof. Harrison Bo Hua Zhu and Prof. Jun Yang. I am also a visiting researcher at Imperial College London, working with Prof. Harrison Bo Hua Zhu and Prof. Samir Bhatt, and I collaborate closely with Prof. Di Wang at KAUST.
My current research focuses on Embodied AI, with a particular interest in efficiently learning from large-scale human multimodal data to achieve general-purpose robotic manipulation.
If you are interested in my research or potential collaboration opportunities, feel free to reach out. I would be happy to chat and collaborate. Please email me at wdong827 (at) connect.hkust-gz.edu.cn.
Selected Publications
View All →Algorithmic Recourse of In-Context Learning for Tabular Data
Wenshuo Dong†, Jiaming Zhang†, Shaopeng Fu, Hongbin Lin, Di Wang, Lijie Hu
ICML
This paper presents the first study of algorithmic recourse for tabular prediction under in-context learning (ICL). It proposes ASR-ICL, a query-efficient black-box framework that generates sparse and actionable recourse for ICL-based models.
Understanding and mitigating cross-lingual privacy leakage via language-specific and universal privacy neurons
Wenshuo Dong, Qingsong Yang, Shu Yang, Lijie Hu, Meng Ding, Wanyu Lin, Tianhang Zheng, Di Wang
EMNLP
This paper investigates cross-lingual privacy leakage in LLMs, showing that models trained on sensitive data in one language can still leak private information when queried in other languages.
Eap-gp: Mitigating saturation effect in gradient-based automated circuit identification
Lin Zhang, Wenshuo Dong, Zhuoran Zhang, Shu Yang, Lijie Hu, Ninghao Liu, Pan Zhou, Di Wang
NeurIPS
This paper proposes EAP-GP, a gradient-based method for automated circuit identification in language models that mitigates the saturation effect in existing attribution methods.
News
Starting my PhD at Hong Kong University of Science and Technology (Guangzhou) 🎉