I'm a Ph.D. student in Machine Learning Department of Carnegie Mellon University. I work on machine learning, especially on interactive learning problems, with my advisors Artur Dubrawski and Aarti Singh. I also work on NLP tasks, especially natural language understanding. Previously I have done research on deep learning/computer vision and game theory.
Contact: yichongx [at] cs.cmu.edu
Selected Publications (Full Publication List)
Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension.
Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu and Jianfeng Gao.
North American Chapter of the Association for Computational Linguistics (NAACL) 2019. Long Oral.
Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information.
Yichong Xu, Hariank Muthakana, Sivaraman Balakrishnan, Aarti Singh and Artur Dubrawski.
35th International Conference on Machine Learning (ICML 2018). Long Oral.
Yichong Xu, Hongyang Zhang, Kyle Miller, Aarti Singh and Artur Dubrawski.
The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS2017).
Efficient Learning from Diverse Sources of Information.
@CMU, Google, Salesforce, JD.com, Facebook, Microsoft, Amazon, Apple (2020).
An overview of my research that spans interactive learning from pairwise comparisons, as well as multitask/transfer learning for natural language understanding.