About Me

Ming Shan is a fifth-year Ph.D. candidate at the Singapore University of Technology and Design (SUTD), under the research supervision of Prof. Roy Ka-Wei Lee. Ming Shan received several prestigious scholarships and awards, including the SUTD President’s Graduate Fellowship and the Singapore Data Science Consortium (SDSC) Dissertation Research Fellowship 2024, which support and fund his Ph.D. studies. Additionally, Ming Shan serves as reviewer for several 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 (LMMs) and post-hoc explanation techniques such as Local Interpretable Model-Agnostic Explanations (LIME), 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