Google ScholarAbout
Previously, I got my PhD from MIT working with Kalyan Veeramachaneni in the Data to AI Lab at LIDS. My research interests are designing sequential algorithms that are robust and reliable as well as aligned with societal values. Before coming to MIT, I completed my undergraduate studies in Computer Science at Washington University in St. Louis, working with Kilian Q. Weinberger .
Publication
Chained Tuning Leads to Biased Forgetting
Using natural sentence prompts for understanding biases in language models
The Backfire Effects of Fairness Constraints
Megan Ung*, Alicia Yi Sun*, Sam Bell, Levent Sagun, Adina Williams
Preliminary version at Next Gen AI Safety @ ICML 2024
Sarah Alnegheimish, Alicia Guo, Yi Sun
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics, July 2022.
Yi Sun, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
ICML 2022 Responsible Decision Making in Dynamic Environment, July 2022.
Towards Reducing Biases in Combining Multiple Experts Online
Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Proceedings of the 30th International Joint Conference on Artificial Intelligence.
[pdf]
Learning Vine Copula For Synthetic Data Generation
Yi Sun, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, February 2019.
[pdf]
Learning fair classifiers in online stochastic settings
Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Neurips 2019 AI for Social Good Workshop.
Contact
Address
Massachusetts Institute of Technology
Building 32-D712
Cambridge, MA 02139
Send an e-mail at:
yis@mit.edu