Li Jin 金力 Principal Investigator 课题组负责人
Associate Professor of Electrical and Computer Engineering
Shanghai Jiao Tong University Global College (prev. UMich Joint Institute)
电气与计算机工程专业副教授
Longbin Bldg. Rm. 424 龙宾楼424室
li.jin at sjtu.edu.cn
Embedded Files
Li received his B.Eng. from Shanghai Jiao Tong University (SJTU) in 2011, M.S. from Purdue University, USA in 2012 (advisor: Dengfeng Sun), and Ph.D. from the Massachusetts Institute of Technology, USA in 2018 (advisor: Saurabh Amin). He was Assistant Professor at the Tandon School of Engineering, New York University, USA from 2018 to 2020. He was also a Visiting Scholar at the University of Erlangen-Nuremberg, Germany in 2016. He joined the SJTU Global College (then UMich Joint Institute) in 2021. He is passionate about teaching and research. He enjoys exploring the unknown alongside students and peers. In his free time, he likes listening to music, playing soccer, and gaming.
2011年获上海交通大学本科学位，2012年获美国普渡大学硕士学位，2018年获美国麻省理工学院博士学位。2018年至2020年曾任美国纽约大学坦登工程学院助理教授，并曾于2016年赴德国埃尔朗根-纽伦堡大学担任访问学者。2021年加入现单位（当时称交大密西根学院）。爱好教学和科研，享受和学生及同行一起探索未知世界的过程。业余时间喜欢听音乐、踢足球、打游戏。
We study the theory of lightweight reinforcement learning methods with applications in smart cities.
我们致力于研究轻量化强化学习理论及其在智慧城市中的应用。
We develop lightweight and secure reinforcement learning algorithms for real‑world systems, using tools from probability theory, stochastic approximation, and game theory to build capable yet interpretable methods. Our research focuses on ensuring reliable convergence between learning and system behavior, while also studying failure modes under data corruption or attacks—with the goal of designing practical, cost‑aware safeguards.
我们致力于为复杂的现实系统构建轻量化且安全的强化学习算法。基于概率论、随机近似与博弈论，研究兼具强大性能与良好可解释性的方法体系，重点分析学习过程与系统动态的协同收敛性。同时，我们探究算法在面临数据污染或恶意攻击时的失效模式，旨在设计实用且具有成本效益的防护机制。
We design decision-making algorithms for networked systems in smart cities such as smart transportation, data networks, and microgrids, with a focus on multi-agent coordination. Our research also examines human behavior within these systems to better understand and optimize human-machine collaboration. Ultimately, we aim to create more adaptive, efficient, and intuitive connected systems.
我们为智能交通、数据网络和微电网等智慧城市中的网络化系统设计智能决策算法，特别专注于多智能体协同策略的研究。同时，我们关注人在这些系统中的行为模式，致力于理解和优化人机协作机制。最终目标是构建更灵活、高效且符合直觉的互联系统。
Our team is diverse and vibrant.
我们的团队背景多元而富有活力。
Zeyi Chen 陈泽奕 Undergraduate student 本科生（2023-）
Zeyi's research integrates reinforcement learning and social norms within multi-agent systems, aiming to steer collective evolution toward superior equilibrium states.
主要研究强化学习与社会规范在多智能体系统中的融合，致力于探索如何驱动群体演化并收敛至更优的协作稳态。
Xiangchen Cheng 成相陈 Ph.D. student 博士生（2022-）
B.Eng. Shanghai Jiao Tong University 上海交通大学本科毕业
Xiangchen's research centers on reinforcement learning and artificial intelligence, with a particular focus on sequencing and decision-making in connected and automated vehicle systems. He aims to develop interpretable and practical learning algorithms to improve the efficiency and safety of vehicle-infrastructure cooperative systems.
研究方向为强化学习与人工智能，重点关注智能网联汽车场景中的排序与决策问题。希望将可解释、可落地的学习算法用于提升车路协同系统的效率与安全性。
Yi Gao 高旖 Ph.D. student 博士生（2024-）
B.Eng. Shandong University 山东大学本科毕业
Yi hails from Nantong, Jiangsu Province. Her research focuses on vehicle platooning, vehicle‑road collaboration, and the application of reinforcement learning in intelligent transportation systems. Outside of her academic work, she is passionate about Chinese calligraphy—holding a Level 10 certification—and counts the movie Life Is Beautiful (La vita è bella) among her favorites. One of her most cherished quotes is: “In me the tiger sniffs the rose.”
江苏南通人。科研兴趣为队列行驶、车路协同，以及强化学习在智慧交通中的应用。兴趣爱好：书法（十级），很喜欢的一部电影《美丽人生》，很喜欢的一句话“心有猛虎，细嗅蔷薇”。
Yizhen He 何奕臻 Undergraduate student 本科生（2022-）
Yizhen is from Wenzhou, Zhejiang Province. His hobbies include food, travel, and gaming. He has a deep interest in artificial intelligence research and believes that even though individual efforts may seem small, each person plays a necessary part in humanity’s collective progress—every independent exploration quietly helps expand the limits of our understanding.
浙江温州人。兴趣爱好是美食、旅游、游戏。对人工智能领域抱有浓厚的研究兴趣，深信个体的力量虽看似渺小，却始终是人类共同进程中不可或缺的一片拼图——每一份独立的探索，都在悄然推动着我们认知的边界。
Zheqi Hu 胡哲绮 Undergraduate student 本科生（2023-）
Zheqi's research interests focus on the modeling and application of reinforcement learning in Markov games, with a particular emphasis on strategy learning and stability issues in the context of multi-agent interactions. In his daily life, he is an avid fan of reading and programming, and he enjoys quickly bringing his ideas to fruition through coding. He hopes to take on tasks more proactively, foster collaboration within the team, and consistently create reusable value in both research and hands-on practice.
科研兴趣聚焦于强化学习在马尔可夫博弈中的建模与应用，关注多智能体交互下的策略学习与稳定性问题。生活中热爱阅读与程序编写，喜欢用代码把想法快速落地。希望在组内更主动承担任务、促进协作，在研究与实践中持续创造可复用的价值。
Zhongqi Huang 黄仲祺 Undergraduate student (UMich double degree) 本科生（密大双学位，2023-）
Zhongqi is interested in using reinforcement learning to address modeling and decision-making problems in complex systems, and he is also curious about how these algorithms can be applied to real-world problems. In his free time, he enjoys playing basketball and traveling, and he also likes to capture moments of life through photography. He looks forward to broadening his perspective and gradually gaining experience through both research and practice.
对于使用强化学习解决复杂系统中的建模与决策问题比较感兴趣，同时也关注相关算法在实际问题中的应用。平时喜欢篮球和旅行，也会用摄影记录生活。期待在科研与实践中不断拓展视野、逐步积累经验。
Wei Jiang 姜惟 Undergraduate student (Tongji University) 本科生（同济大学，2022-）
Wei enjoys playing badminton and swimming, has just gotten started with fitness training and basketball, and has an intermediate skill level in string instruments. Her research interests are interdisciplinary. She is highly motivated and has some hands-on experience with both software and hardware. In terms of personality, she identifies as 55% Extraverted, 64% Intuitive, 56.5% Feeling, and 68% Judging. She is also an avid stuffed animal collector.
擅长羽毛球、游泳，健身小白，篮球初级，弦乐中级。对学科交叉的研究感兴趣，拥有超强执行力，软硬件都懂一些。性格是55%的e，64%的n，56.5%的f，68%的j，毛绒动物的狂热爱好者。
Yifan Fiona Jiang 蒋意凡 Undergraduate student 本科生（2022-）
Fiona's research centers on reinforcement learning and autonomous driving, tackling how intelligent agents learn and make decisions in complex environments. Outside of her academic work, she loves discovering great food, traveling, and immersing herself in different city cultures. She draws inspiration from life on the road and embraces the continual process of exploration in both her research and her adventures.
研究方向聚焦于强化学习与自动驾驶，智能体在复杂环境中的学习与决策问题。科研之外喜欢寻找美食、旅行和体验不同的城市文化，享受在路上获得灵感、在研究中不断探索的过程。
Zimeng Mao 毛梓萌 Undergraduate student 本科生（2022-）
Research isn’t just part of Zimeng's daily routine—it’s a practice of constant observation, careful thinking, and every now and then, a sudden breakthrough. She loves the precision of math and logic, but also enjoys savoring a great meal or catching a live show. Life, after all, calls for its own kind of focus: the kind where she really lives the moment and look back on it with purpose. Maybe reason and feeling aren’t so different after all. Together, they’ve helped her become exactly who she wants to be.
科研是每天的日常，也是持续观察、推敲和偶尔顿悟的过程。喜欢数理逻辑，也喜欢细品美食，听演唱会——生活同样需要沉下心去“体会”与“复盘”。理性与感受，或许本就是一回事，它们陪伴她成为了喜欢的自己。
Jiasheng Pan 潘家晟 Ph.D. student 博士生（2024-）
B.S. Shanghai Jiao Tong University 上海交通大学本科毕业
In his research, Jiasheng aims to make meaningful contributions throughout his academic career. He also hopes to leave his mark in a future where AI is deeply integrated into everyday life. Outside of research, he looks forward to continuing to find joy and satisfaction in his personal projects and past work.
在科研方面，目前希望能够在科研的生涯中做出一些有趣的成果。同时，也希望在未来AI深度介入人类生活的场景中，能够留下一些自己的印记。日常生活中，能保持从过去的一些作品中获得快乐也是他所期望的。
Haotian Peng 彭昊天 Ph.D. student 博士生（2023-）
B.Eng. Shanghai Jiao Tong University 上海交通大学本科毕业
Haotian's research focuses on the cross-application of game theory, opinion dynamics, and reinforcement learning in energy systems. He works on solving multi-agent decision-making problems within social networks, particularly in areas like microgrid demand-side response and peer-to-peer (P2P) energy trading. In his spare time, he loves discovering good food, playing card games, and traveling.
主要研究博弈论、观点动力学与强化学习在能源系统中的交叉应用，解决微电网需求侧响应及P2P交易中与社交网络相关的多智能体决策问题。业余时间喜欢干饭、打牌和旅游。
Zhihao Song 宋至豪 Ph.D. student 博士生（2022-）
B.Eng. Shanghai Jiao Tong University 上海交通大学本科毕业
Zhihao's research interest is reinforcement learning for microgrids, with emphasis on algorithm design, theoretical analysis, and simulation validation.
研究方向为强化学习算法在微电网中的应用，重点关注算法设计、理论性质和仿真验证。
Yidan Wu 武一丹 Ph.D. student 博士生（2023-）
B.Eng. Tongji University 同济大学本科毕业
Yidan is driven by a fascination with the cognitive decision-making processes of intelligent beings, which guides her research in network-based multi-agent reinforcement learning. She stays active through tennis, badminton, and hiking, and also enjoys quieter pursuits like literature, philosophy, sci-fi, and calligraphy—naturally balancing both sides of her personality. She approaches the unknown and the natural world with a sense of awe and curiosity, always navigating the space between logic and freedom ;)
研究方向为基于网络的多智能体强化学习。好奇智慧生命认知决策原理。热爱网羽爬山，亦喜文哲科幻书法，动静皆宜。对未知与大自然常怀敬畏并充满好奇，在逻辑与自由间寻找平衡;)
Sihan Yang 杨斯涵 M.S. student 硕士生（2024-）
B.Eng. Xi'an Jiao Tong University 西安交通大学本科毕业
Sihan's current work centers on reinforcement learning and multi-agent systems. Outside the lab, she enjoys exploring different ice cream flavors and highly recommends the yuzu sorbet from M Stand.
现研究方向主要为强化学习与多智能体系统。平日喜欢去发掘不同口味的冰淇淋，强推M Stand的柚子味冰淇淋
Yu Yu 俞瑜 M.S. student 硕士生（2025-）
B.Eng. Wuhan University 武汉大学本科毕业
Yu's current research directions mainly focus on reinforcement learning and neural architecture search. On ordinary days, she enjoys playing table tennis, billiards and discovering good food.
现研究方向主要为强化学习与神经架构搜索。平日喜欢打乒乓、桌球和干饭。
Puchen Xu 徐浦晨 Ph.D. student 博士生（2023-）
B.Eng. Shanghai Jiao Tong University 上海交通大学本科毕业
Puchen's research primarily centers on the security of cyber-physical systems and networked control. He also maintains a strong interest in applying reinforcement learning to the field of automatic control.
主要研究方向是信息物理系统和网络控制的安全性问题。此外，他对于强化学习在自动控制中的应用也很感兴趣。
Yuzhen Zhan 詹裕真 M.S. student 硕士生（2023-）
B.Eng. Wuhan University 武汉大学本科毕业
Yuzhen's research focuses on game-theoretical model of adversarial dynamic and applying reinforcement learning methods to solve practical security challenges in cyber-physical systems. In particular, she is interested in theoretical guarantees of algorithms.
科研方向聚焦于对抗动态博弈理论模型，并运用强化学习方法解决网络物理系统中的实际安全挑战，尤其关注算法的理论保障。
Yule Zhang 张羽乐 Ph.D. student 博士生（2025-）
B.Eng. Southern University of Science and Technology 南方科技大学本科毕业
Yule's research focuses on the application of reinforcement learning in intelligent connected systems such as microgrids. Her personal interests include watching anime and playing badminton.
主要科研兴趣是强化学习在智能网联系统（如微电网）中的应用。兴趣爱好包括看番、羽毛球等。
Our incredible alumni are continuing their explorations across the world.
我们出色的毕业生们正在世界各地继续他们的探索之旅。
Yumeng Bai 白雨萌 B.Eng. alumna 本科毕业生（2022）
Yumeng is a direct Ph.D. student in Autonomy and Control at Purdue University, co-advised by Prof. Yiheng Feng and Prof. Dengfeng Sun. She holds a B.S. in Electrical and Computer Engineering from Shanghai Jiao Tong University (2022), where she minored in Data Science and was honored as a Shanghai Outstanding Graduate. Her prior research with Prof. Li Jin focused on game theory for cybersecurity in transportation systems, resulting in publications at leading IEEE conferences. She is currently working on air-ground traffic cooperation and cybersecurity in intelligent transportation systems.
现为美国普渡大学航空航天学院直博生，研究方向为自主与控制，师从冯毅恒教授与孙登峰教授。她于2022年获得上海交通大学密西根学院电气与计算机工程学士学位，辅修数据科学，并获评上海市优秀毕业生及交通大学“莙政学者”荣誉。她曾与金力教授合作开展基于博弈论的智能交通系统网络安全研究，相关成果已在IEEE决策与控制会议等权威会议上发表。目前，她主要致力于空陆交通协同与智能交通系统网络安全等领域的研究。
Mladen Čičić Visiting Ph.D. student 博士访问生（2019）
Mladen is a maître de conférences (associate professor) in the Systems and Control group at the Laboratory of Signals and Systems, CentraleSupélec, Université Paris-Saclay. His research focuses on modeling and control of mixed traffic. He was previously a postdoctoral fellow at the University of California, Berkeley, and conducted postdoctoral research at GIPSA-lab in France. He earned his Ph.D. from KTH Royal Institute of Technology in 2021 and holds B.Sc. and M.Sc. degrees in Electrical Engineering and Computer Science from the University of Belgrade.
巴黎萨克雷大学中央理工-高等电力学院信号与系统实验室系统与控制组的副教授。其研究主要围绕混合交通建模与控制。他曾于加州大学伯克利分校担任博士后，并在法国GIPSA实验室开展研究工作。他于2021年在瑞典皇家理工学院获得博士学位，本科与硕士均毕业于贝尔格莱德大学电气工程与计算机科学专业。
Yang Liu 刘扬 B.Eng. alumna 本科毕业生（2021）
Yang is currently an Algorithm Engineer at Meituan. She completed her undergraduate studies at Shanghai Jiao Tong University and subsequently earned her Ph.D. from The Hong Kong University of Science and Technology. During her doctoral research, she focused on operations research and optimization for on-demand mobility services. Her work integrated operations research, machine learning, and economic theory to address collaborative optimization problems in smart mobility services and urban logistics systems, covering key areas such as collaborative pricing, order dispatching, and vehicle scheduling. Currently, her focus has shifted to algorithm research and application in the field of user growth.
现任美团算法工程师。本科毕业于上海交通大学，随后于香港科技大学取得博士学位，期间专注于按需出行服务的运筹优化研究。具体方向融合了运筹优化、机器学习与经济学理论，旨在解决智慧出行服务与城市物流系统的协同优化问题，涵盖协同定价、订单分配与车队调度等关键领域。目前工作重点转向用户增长方向的算法研究与应用。
Junyi Sha 沙君怡 B.S. alumna 本科毕业生（2021）
Junyi is a Ph.D. candidate at MIT, affiliated with the Center for Computational Science and Engineering (CCSE) and the Laboratory for Information and Decision Systems (LIDS), advised by Professor David Simchi-Levi. She also collaborates with Dr. Josué C. Velázquez Martínez at the Center for Transportation and Logistics (CTL). Before MIT, she earned my bachelor’s degree in Mathematics and Computer Science from the Courant Institute of Mathematical Sciences at New York University. Her research focuses on developing data-driven methods that integrate computer vision, machine learning, and operations research to improve demand forecasting and product design decisions in fashion and retail industries.
现于麻省理工学院攻读博士学位，隶属于计算科学与工程中心和信息与决策系统实验室，师从David Simchi-Levi教授。同时与运输与物流中心的Josué C. Velázquez Martínez博士保持研究合作。其研究专注于开发数据驱动的方法，融合计算机视觉、机器学习与运筹学，以提升时尚和零售行业中的需求预测与产品设计决策能力。
Haoran Anthony Su 苏浩然 Ph.D. alumnus 博士毕业生（2024）
Anthony obtained his B.S. and M.S. degrees from the University of California, Berkeley and Ph.D. from New York University Tandon School of Engineering. He is a recipient of the Dwight David Eisenhower Transportation Fellowship. He studied agent-based mixed logit framework for travel behaviour modeling with large dataset. He is not working at TikTok.
本科、硕士毕业于美国加州大学（伯克利），博士毕业于美国纽约大学坦顿工学院，曾获德怀特·戴维·艾森豪威尔交通奖学金。研究方向为基于智能体的混合Logit框架，利用大规模数据集进行出行行为建模研究。 现任职于TikTok。
Yanwei Sun 孙严伟 Ph.D. visiting student 博士访问生（2021-22）
Yanwei is a Ph.D. student in Analytics & Operations at Imperial College Business School, advised by Professors Jiahua Wu and Chiwei Yan. He was a visiting scholar at UC Berkeley in 2024–2025. His research focuses on designing platforms and market mechanisms for strategic settings, with emphasis on information design in operations and AI-enhanced mechanism design.
英国帝国理工学院商学院数据分析与运营方向博士在读，师从吴佳华与鄢驰为老师，并于2024–2025学年在加州大学伯克利分校进行访问研究。主要关注面向策略性环境的平台与市场机制设计，重点包括运营中的信息设计以及人工智能增强的机制设计。
Yu Tang 唐钰 Ph.D. alumnus 博士毕业生（2025）
Yu received the B.Eng. and M.S. degrees in transportation engineering from Tongji University, Shanghai, China, in 2016 and 2019, respectively. He is currently working toward the Ph.D. degree in transportion systems with the Tandon School of Engineering, New York University, New York, NY, USA. His research interests include using ideas from stochastic processes and dynamic control to design resilient intelligent transportation systems.
于2016年与2019年先后在同济大学获得交通工程学士与硕士学位，2025年获美国纽约大学坦登工程学院交通系统专业博士学位。研究主要基于随机过程与动态控制理论，致力于韧性智能交通系统的设计与优化。
Qian Xie 谢倩 M.S. alumna 硕士毕业生（2021）
Qian is a Ph.D. candidate at Cornell University, advised by Ziv Scully. Her research integrates probabilistic machine learning and operations research to study decision-making under uncertainty. She develops data-driven methods for optimal learning and information acquisition, grounded in applied probability and optimal decision theory. She holds an M.S. from NYU and a B.Eng. from Tsinghua University.
康奈尔大学博士在读，导师为 Ziv Scully。研究方向结合概率机器学习与运筹学，聚焦不确定性下的决策问题。致力于通过数据驱动方法研究最优学习与信息获取，理论基础源于应用概率与最优决策理论。纽约大学硕士，清华大学本科。
Xi Xiong 熊溪 Ph.D. alumnus 博士毕业生（2021）
Xi is currently a Research Professor of Transportation Engineering at Tongji University and a Visiting Researcher in the Department of Engineering Science at the University of Oxford. Prior to joining Tongji, he was a Postdoctoral Fellow at the Harvard Kennedy School. He holds a Ph.D. in Transportation Engineering from New York University, an M.Sc. from Tsinghua University, and a B.Sc. from Jilin University. He is also a co-founder of LangRun.AI.
现为同济大学交通工程专业特聘研究员、博士生导师，兼任牛津大学工程科学系访问研究员。曾于哈佛大学肯尼迪学院担任博士后研究员，拥有纽约大学交通工程博士学位、清华大学硕士学位及吉林大学学士学位。LangRun.AI的联合创始人。
Yichuan Zou 邹一川 M.S. alumnus 硕士毕业生（2025）
Yichuan currently works as a Large Model Application Algorithm Engineer at Kuaishou, where he specializes in optimizing click-through rates for short-video push content. He earned his Bachelor’s degree in Software Engineering from Huazhong University of Science and Technology. During his Master’s program, his research focused on the application of reinforcement learning in traffic flow control scenarios. His M.S. thesis title is "Macriscopic Traffic Flow Model-Based Reinforcement Learning for Vehicle Platoon Control in Mixed-autonomy Traffic."
现任快手公司大模型应用算法工程师，工作方向为短视频推送文案的点击率优化。本科毕业于华中科技大学软件工程专业。硕士期间研究方向为强化学习在交通流控制场景的应用，毕业论文标题为《面向混合自动驾驶交通的车辆编队控制：基于宏观交通流模型的强化学习方法 》。
Page updated
Google Sites
Report abuse