About

I am an assistant professor at Northeastern University in the Khoury College of Computer Sciences. I received my Ph.D. in Computer Science from Stanford University and my Bachelor's degree in Computer Science and Technology from Shanghai Jiao Tong University. Subsequently, I did a postdoc at the University of Pennsylvania in the Statistics and Data Science department at the Wharton School.

Research interests

I work on a broad range of topics at the intersection of machine learning, algorithms, and large-scale networks. I am passionate about advancing technology; my recent focus includes: (i) foundation models and language models, including both theoretical understand and new algorithms for multitask learning, supervised fine-tuning, and in-context learning. I am particularly interested in understanding how neural networks learn to extract information from data, and how this knowledge transfers to downstream tasks. To this end, we are developing a Hessian-based computational framework where we measure the second-order information such as the spectral statistics of the loss Hessian, and apply this framework to downstream settings. (ii) learning and reason on large-scale networks. (iii) Algorithmic game theory including learning from ranking data, incentives in data collection. For more information, please check out the research overview page and my CV.

I draw on techniques from optimization, learning theory, probability, and mechanism design to advance the foundations of machine learning. Application areas include natural language processing and transportation.

I enjoy working on technically challenging problems, while striving for broader impacts by creating new knowledge that will benefit the society, as well as fostering the next generation of engineers and researchers. I support accessible and reproducible research.

Recent updates

Talk slides about our recent line of work on a Hessian view of supervised fine-tuning, task attribution, and RL.
New paper on efficient kernel methods for language model and data attribution.
A new paper using a self-normalization estimator for matrix completion from very sparse observations.
A list of older logs.
Note for prospective students: I'm always looking for students who are interested in working with me. If you are a student at Northeastern, please feel free to contact me.

Recent professional services

Conference Area Chairs: NeurIPS, ICML, KDD, AISTATS, AAAI

Journal Area Editors: Transactions on Machine Learning Research, Journal of Data-Centric Machine Learning Research.

Conference Organization: INFORMS session organizer and session chair.

Referee and Panel Service: Journal of Machine Learning Research, National Science Foundation.