Ph.D. student at Utrecht University Email: y [dot] du [at] uu [dot] nl Address: BBG 5.05, 3584CC Utrecht, the Netherlands [Google Scholar] [CV] |
I am a fourth-year Ph.D. student at Utrecht University, advised by Dr. Dong Nguyen.
My current research interests lie within Natural Language Processing and Machine Learning
(esp. efficient and robust NLP models).
Besides, I am broadly interested in Computational Social Science.
Before joining UU, I received both my bachelor’s (Psychology, 2017) and my master’s (Computer Science, 2020, advised by Dr. Yuanbin Wu) degrees from East China Normal University.
Pre-prints
Yupei Du, Albert Gatt, and Dong Nguyen. FTFT: efficient and robust Fine-Tuning by transFerring Training dynamics. arXiv pre-print. [pdf]
Conference Papers
Yupei Du and Dong Nguyen. Measuring the Instability of Fine-Tuning. ACL 2023. [pdf]
Yupei Du, Qi Zheng, Yuanbin Wu, Man Lan, Yan Yang, Meirong Ma. Understanding Gender Bias in Knowledge Base Embeddings. ACL 2022. [pdf]
Yupei Du, Qixiang Fang, Dong Nguyen. Assessing the Reliability of Word Embedding Gender Bias Measures. EMNLP 2021. [pdf]
Yupei Du, Yuanbin Wu, Man Lan. Exploring Human Gender Stereotypes with Word Association Test. EMNLP 2019. [pdf]
Program Committee (2021-): ACL, EMNLP, NAACL, EACL.
Outstanding Reviewer: ACL 2022.
TA of Methods in Artificial Intelligence Research, 2020 - 2021. Utrecht University.
TA of Applications of Machine Learning, 2021 - 2024. Utrecht University (Distinguished teaching award in 2022).
TA of Human-centered Machine Learning, 2021 - 2024. Utrecht University.
TA of Transformers: Applications in Language and Communication, 2024. Utrecht University.
I instructed a lecture on "Efficient LLMs" [Slides].Applied scientist intern at Amazon.com Inc., Berlin, Germany. Nov. 2022 - May. 2023. Mentored by Prof. Dr. Ziawasch Abedjan.
Research intern at Sogou Inc., Hangzhou, China. Jul. 2019 - Jan. 2020.