Xiaoyi Qu (曲笑一)
PhD student
Department of Industrial and Systems Engineering,
Lehigh University,
200 W Packer Ave. Bethlehem, PA 18015.
Email: xiq322@lehigh.edu
Xiaoyi Qu (曲笑一)
PhD student
|
|
Xiaoyi Qu is a third-year Ph.D. student in the Department of Industrial and Systems Engineering at Lehigh University, advised by Prof. Daniel P. Robinson. He has industry experience through internships at Neusoft Medical in 2019 and, more recently, at Microsoft's Applied Sciences Group (ASG) in 2024, where he worked on model compression. His research centers on constrained structured optimization and efficient AI techniques such as pruning and quantization. More recently, he has become particularly interested in improving the training and inference efficiency of large language models (LLMs).
Ph.D., Industrial Engineering, Lehigh University, Bethlehem, PA, USA, 2022–current
B.S., Mathematical Science, University of Michigan, Ann Arbor, MI, USA, 2019–2022
Computational Mathematics, Dalian University of Technology, Dalian, China, 2017–2019
|
A Proximal Gradient Method for Equality Constrained Optimization [  ] Yutong Dai, Xiaoyi Qu, Daniel P. Robinson. 2025 Van Hoesen Family Best Publication Award (Honorable Mention) Accepted by SIAM Journal on Optimization (SIOPT) , 2025 [arXiv] |
|
Automated Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression Xiaoyi Qu, David Aponte, Colby Banbury, Daniel P. Robinson, Tianyu Ding, Kazuhito Koishida, Ilya Zharkov, Tianyi Chen. Computer Vision and Pattern Recognition (CVPR), 2025 [Paper] [arXiv] [Code] |
|
HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning Xiaoyi Qu, David Aponte, Colby Banbury, Jongwoo Ko, Tianyu Ding, Yong Ma, Vladimir Lyapunov, Ilya Zharkov, Luming Liang, Tianyi Chen. arXiv preprint, 2024 [arXiv] [Code] |
|
A Proximal Gradient Method for Regularization Optimization with General Constraints [ ] Frank E. Curtis, Xiaoyi Qu , Daniel P. Robinson. Working Paper. (Coming soon) |
Journal Reviewer: Optimization and Enigneering, Computational Optimization and Applications
Conference Reviewer: Constrained Optimization for Machine Learning (COML) Workshop, NeurIPS 2025