About Me

Ming Shan is a fifth-year Ph.D. candidate at the Singapore University of Technology and Design (SUTD), supervised by Prof. Roy Ka-Wei Lee. He is a recipient of the SUTD President’s Graduate Fellowship and the Singapore Data Science Consortium (SDSC) Dissertation Research Fellowship 2024. His research has been published in top conferences such as WWW, ACM Multimedia, EMNLP, and ICLR. Ming Shan also serves as a reviewer for top-tier conferences and co-organizes SSNLP 2024 and 2025.

His Ph.D. research focuses on developing trustworthy and explainable approaches for hateful content moderation, particularly in multimodal settings. By leveraging large multimodal models and post-hoc explanation techniques, his work improves both detection accuracy and interpretability while mitigating biases in model predictions. Ultimately, his research contributes to online trust and safety by improving the explainability of AI-driven moderation systems, ensuring fairer and more accountable decision-making. The findings have significant implications, particularly in content moderation, where balancing performance, fairness, and explainability is essential for real-world deployment.

Last Updated: 25th February 2025