I am an Applied Scientist at Amazon AWS where my work focuses on scaling customer needs through Generative AI and LLM agents. My research has always revolved around problems in machine learning and natural language processing. I have solid industry experience, multiple first-author publications in top conferences, and strong foundation in mathematics and algorithms.
I obtained my Ph.D. degree in Computer Science at the University of Maryland under the guidance of Jordan Boyd-Graber. I also worked closely with Benjamin Van Durme from Johns Hopkins and Hsuan-Tien Lin from NTU. During my PhD, I worked on the intersection of transfer learning and interactive learning. The focus was on adapting NLP models for new domains, languages, and tasks through human feedback.
My undergraduate degree at Cornell University was in mathematics. I graduated with cum laude honors distinction and a minor in Computer Science. During college, I also was President of Cornell Wushu club.
Outside of computer science research, I enjoy activities like mountain climbing, rock climbing, badminton, and running.
Fun fact: I have an Erdös number of 3.
I obtained my Ph.D. degree in Computer Science at the University of Maryland under the guidance of Jordan Boyd-Graber. I also worked closely with Benjamin Van Durme from Johns Hopkins and Hsuan-Tien Lin from NTU. During my PhD, I worked on the intersection of transfer learning and interactive learning. The focus was on adapting NLP models for new domains, languages, and tasks through human feedback.
My undergraduate degree at Cornell University was in mathematics. I graduated with cum laude honors distinction and a minor in Computer Science. During college, I also was President of Cornell Wushu club.
Outside of computer science research, I enjoy activities like mountain climbing, rock climbing, badminton, and running.
Fun fact: I have an Erdös number of 3.
News
12/24: Work on multi-agent collaboration is presented at re:Invent 2024 by CEO Matt Garman and details are released in technical report10/22: PhD thesis is now published online
09/22: Joined Amazon AWS AI as an Applied Scientist in New York
07/22: Successfully defended PhD thesis, "Transfer Learning in NLP through Interactive Feedback"
Publications
See my Google Scholar profile for up-to-date list of papers.- Michelle Yuan. Transfer Learning in Natural Language Processing through Interactive Feedback. PhD Thesis, University of Maryland, 2022.
[paper]
- Michelle Yuan, Patrick Xia, Chandler May, Benjamin Van Durme, and Jordan Boyd-Graber. Adapting Coreference Resolution Models through Active Learning. Association for Computational Linguistics (long), Oral Presentation, 2022.
[paper] [arxiv] [code] [video]
- Michelle Yuan, Hsuan-Tien Lin, and Jordan Boyd-Graber. Cold-start Active Learning through Self-Supervised Language Modeling. Empirical Methods of Natural Language Processing (long), 2020.
[paper] [arxiv] [code] [video]
Last updated:
Website design: Michelle Yuan
Photography: Michelle Yuan