刘鑫本科毕业于湖南大学电子信息工程专业（2011），硕士毕业于中国科学院大学信息与信号处理专业（2014），博士毕业于美国亚利桑那州立大学电子工程专业（2019），之后在美国密歇根大学安娜堡分校从事博士后研究工作，于2021年8月加入上海科技大学信息学院担任助理教授、研究员、博士生导师。

主要研究方向为随机系统建模与优化、强化学习及其在网络系统、推荐广告竞价、大语言模型中的应用。近年来在领域内重要期刊和会议上发表论文30余篇，包括Operations Research、COLT、NeurIPS、ICML、SIGMETRICS等。主持国家自然科学基金青年/面上项目，腾讯犀牛鸟广告专项，CCF-腾讯犀牛鸟基金等。指导课题组学生入选腾讯犀牛鸟精英人才项目并获优秀奖、多人次获得国家研究生奖学金。

安全智能决策 (I am a Safe Bandit/RLer)

X. Peng et al. Towards Achieving Optimal Strong Regret and Violation via Computationally Efficient Model-Free RL. ICML 2026.

H. Guo et al. Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints. ICML 2025.

H. Guo et al. Stochastic Constrained Contextual Bandits via Lyapunov Optimization Based Estimation to Decision Framework. COLT 2024.

H. Zhang et al. Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage. NeurIPS 2024.

大语言模型微调与路由（Route with Brains, Align with Reins）

L. Zu et al. BARouter: A Budget-adaptive Online Large Language Model Router Framework. WWW 2026.

X. Peng et al. Enhancing Safety in RLHF via Rectified Policy Optimization. NeurIPS 2025.

推荐与广告竞价（Bidding is Money）

H. Wu*, W. Ou*, H. Guo* et al. GRB: A Generative Reinforcement Bidding Framework for Multi-Channel Online Advertising. KDD 2026.

H. Guo*, H. Zhang* et al. Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework. ICLR 2026.

随机系统建模与优化 (Queues Never Fade Away)

X. Liu (with GPT5.5 Pro). Zero-waiting Load Balancing with Coxian-2 Service in the Super–Halfin–Whitt Regime. 2026.

X. Liu et al. Large-System Insensitivity of Zero-Waiting Load Balancing Algorithms. Stochastic Systems, 2024.

X. Liu and L. Ying. Universal Scaling of Distributed Queues Under Load Balancing in the Super-Halfin-Whitt Regime. IEEE Trans. on Networking, 2022.

X. Liu and L. Ying. Steady-State Analysis of Load Balancing Algorithms in the Sub-Halfin-Whitt Regime. Journal of Applied Probability, 2020.

A. Braverman, et al. Empty-Car Routing in Ridesharing Systems. Operations Research, 2019.

星号*表示共同第一作者，下划线表示课题组成员，详细科研成果请参考 https://liuxincell.github.io/

算法与数据结构（CS101）

在线优化与学习（CS245）