Selected Papers and Preprints: (Author name is listed in alphabetical order)
Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics,
Zijie Zhou [Paper]
ICML 2026
Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale,
Tianci Bu, Yuan Lyu, Zixi Chen, Chendong Song, Hong Liang, Tsepten Gurung, Yuwei Fan, Yinyu Ye, Zijie Zhou [Paper]
Neurips 2026
Best Student Paper Award in The 3rd Academic Conference on Data Science and Operations Intelligence of the Operations Research Society of China
AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration,
Chendong Song, Tianci Bu, Meixuan Wang, Zijie Zhou [Paper]
Neurips 2026
Best Young Faculty Paper Award in The 3rd Academic Conference on Data Science and Operations Intelligence of the Operations Research Society of China
Queueing-Theoretic GPU Provisioning for Disaggregated Multimodal LLM Serving,
Sunkai Lyu, Jiaming Fang, Zijie Zhou
Best Student Paper Finalist in The 3rd Academic Conference on Data Science and Operations Intelligence of the Operations Research Society of China
Online Linear Programming for Multi-Objective Routing in LLM Serving,
Zixi Chen, Yinyu Ye, Zijie Zhou [Paper]
ICML 2026
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints,
Chengyi Nie, Nian Si, Zijie Zhou [Paper]
ICML 2026
AI-Assisted Discovery of a Polynomial Lyapunov Potential for the Antiferromagnetic Potts Model,
Chendong Song, Chenlin Gu, Zijie Zhou [Paper]
ICML 3rd AI for Math Workshop, 2026
A Universal Load Balancing Principle and Its Application to Large Language Model Serving,
Zixi Chen, Tianci Bu, Chendong Song, Xin Lu, Yinyu Ye, Zijie Zhou [Paper]
Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice,
Li Kong, Qi Qi, Yinyu Ye, Zijie Zhou [Paper]
Neurips 2026
Online Evaluation of LLMs via Dyadic Designs,
Jinglong Zhao, Zijie Zhou
Neurips 2026
Theoretically Optimal Attention/FFN Ratios in Disaggregated LLM Serving,
Chendong Song, Meixuan Wang, Hang Zhou, Hong Liang, Yuan Lyu, Zixi Chen, Yuwei Fan, Zijie Zhou [Paper]
LLM Serving Optimization with Variable Prefill and Decode Lengths,
Meixuan Wang, Yinyu Ye, Zijie Zhou [Paper]
INFORMS Undergraduate Operations Research Prize Competition Finalist
Major Revision in Manufacturing & Service Operations Management
Adaptively Robust LLM Inference Optimization under Prediction Uncertainty,
Zixi Chen, Yinyu Ye, Zijie Zhou [Paper]
Online Scheduling for LLM Inference with KV Cache Constraints,
Patrick Jaillet, Jiashuo Jiang, Konstantina Mellou, Marco Molinaro, Chara Podimata, Zijie Zhou [Paper]
NeurIPS 2024 Workshop on Statistical Frontiers of LLM and Foundation Models
Pigeonhole design: Balancing sequential experiments from an online matching perspective,
Jinglong Zhao, Zijie Zhou [Paper]
Management Science, 2025
Online Resource Allocation with Convex-Set Advice,
Negin Golrezaei, Patrick Jaillet, Zijie Zhou [Paper]
Operations Research, 2026
When Should you Offer an Upgrade: Online Upgrading Mechanisms for Resource Allocation,
Patrick Jaillet, Chara Podimata, Andrew Vakhutinsky, Zijie Zhou [Paper]
WINE 2024, INFORMS Service Science Best Student Paper Competition Finalist
Near-Optimal Primal-Dual Algorithms for Quantity-Based Network Revenue Management,
Rui Sun, Xinshang Wang, Zijie Zhou [Paper]
Major Revision in Mathematics of Operations Research
Grace Period is All You Need: Realize Individual Fairness in Revenue Management,
Patrick Jaillet, Chara Podimata, Zijie Zhou [Paper]
WINE 2024