Cantao Su is a PhD researcher under the supervision of Dr. Dong Nguyen, working on the DataDivers project, exploring how linguistic diversity—across dialects, registers, and styles—affects fairness and robustness in NLP models. He is also a member of the NLP and Society Lab within the Department of Information and Computing Sciences at Utrecht University. His research combines sociolinguistic insights with neural language modeling to better represent underrepresented language varieties. 

He holds a Master’s degree in Voice Technology from the University of Groningen, where he specialized in deep learning for speech recognition, particularly for people with Parkinson's disease, and a Bachelor's degree in Korean Language and Literature from Beijing International Studies University.