Xiaoyi Qu (曲笑一) PhD candidate Department of Industrial and Systems Engineering, Lehigh University, 200 W Packer Ave. Bethlehem, PA 18015. Email: xiq322@lehigh.edu

Biography

Xiaoyi Qu is a fourth-year Ph.D. candidate in the Department of Industrial and Systems Engineering at Lehigh University, under the supervision of Prof. Daniel P. Robinson. His research focuses on two primary areas: (i) the development and theoretical analysis of first-order methods for solving constrained structured optimization problems, and (ii) model optimization techniques (e.g., structured pruning and quantization-aware training) for deep neural networks. In 2026, he worked as a machine learning engineer intern at Genies Inc, where he focused on inference acceleration and model optimization for an internal 3D generation pipeline. In 2024, he worked as a research intern with Microsoft's Applied Sciences Group (ASG), where his work centered on joint pruning and quantization techniques. Prior to this, he was an acoustic test intern at Neusoft Medical in 2019.

Education

• 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

Publication and Preprints

	Multi-Agent Consensus Matrix Modeling for Medical Decision-Making: A Role-Specialized LLM Framework for Oncology MDT Consultations Ziyi Ni, Yiming Yan, Xiaoyi Qu, Yanzhan Chen, Chuang Liu. ICLR 2026 Workshop on MALGAI [Paper]
	A Proximal Gradient Method for Equality Constrained Optimization [] Yutong Dai, Xiaoyi Qu, Daniel P. Robinson. SIAM Journal on Optimization (SIOPT), 2025 2025 Van Hoesen Family Best Publication Award (Honorable Mention) [Paper] [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]
	StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths Tianyi Chen, Sihan Chen, Xiaoyi Qu, Dan Zhao, Ruomei Yan, Jongwoo Ko, Luming Liang, Pashmina Cameron. arXiv preprint, 2026 [arXiv] [Code]
	A Proximal Gradient Method for Solving Regularized Optimization with General Constraints [] Frank E. Curtis, Xiaoyi Qu , Daniel P. Robinson. arXiv preprint, 2025 [arXiv]
	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]

Professional Service

Journal Reviewer:

• Optimization and Engineering
• Computational Optimization and Applications
• IEEE Transactions on Circuits and Systems for Video Technology
• INFORMS Journal on Optimization
• Machine Learning

Conference Reviewer:

• Constrained Optimization for Machine Learning (COML) Workshop, NeurIPS 2025
• ICASSP 2026
• Workshop on Multi-Agent Learning and Its Opportunities in the Era of Generative AI, ICLR 2026

Notes

• Inference System Part I: Continuous Batching (连续批处理)

• Inference System Part II: Inference Scheduling (推理调度)

• Inference System Part III: PD Disaggregation (PD分离)

• Inference System Part IV: Inference Parallelism (推理侧并行)

• Quantization Part I: Dequantization Inference-W4A16 (反量化推理)

• Long context : Long Context Extrapolation (长上下文外推)

Non-academic Stuff

• I am originally from northeastern China.

• I once drove cross-country and back, making the full round trip from the East Coast to the West Coast.