基本信息
| 姓名：赵梦辰 办公室：大学城校区B8-413 E-mail: zzmc@scut.edu.cn 所在团队：智能软件与机器人团队 个人主页：https://batmanzzmc.github.io/
|
个人简介
赵梦辰，现任华南理工大学软件学院副教授，硕士/博士生导师。2019年博士毕业于新加坡南洋理工大学计算机科学与工程学院，师从安波教授（https://personal.ntu.edu.sg/boan/index.html）。2014年本科毕业于中山大学应用数学系。2019-2023年曾先后在腾讯广告和华为诺亚方舟实验室担任高级研究员。主要研究方向是强化学习，智能体与多智能体系统，基础模型以及这些技术在推荐系统，数字人和机器人等领域的应用。近年来，在人工智能顶级会议(ICML,ICLR,NeurIPS,AAAI,IJCAI,CVPR,WWW,CIKM,WSDM)和期刊 (IEEE Trans. on Cybernetics, Trans. on Dependable and Secure Computing, IEEE Intelligent Systems)上发表了20余篇学术论文。长期担任ICML,ICLR,NeurIPS,AAAI,IJCAI,CVPR等顶级会议和期刊的Committee Member和审稿人。
欢迎有志于从事强化学习，多智能体系统，大模型Agent及应用方向的本科生、硕博研究生加入我的课题组，本课题组有丰富的实习和国际交流资源。现招收2025年入学博士生1-2人，硕士生2-3人（含中组部计划），欢迎与我联系，来信请附上个人简历。”
学习经历
2014年8月-2019年1月，南洋理工大学，计算机科学与工程，博士
2010年9月-2014年6月，中山大学，数学与应用数学，本科
工作经历
2024年1月-至今，华南理工大学软件学院，副教授
2020年3月-2024年1月，华为诺亚方舟实验室，高级研究员
2019年1月-2020年3月，腾讯广告，高级工程师
获奖情况
南洋理工大学杰出博士论文奖，2019
IEEE Conference on Games Fighting Game AI Competition冠军，2020
Microsoft Collaborative AI Challenge冠军，2017
发表论文
1.Improving Unsupervised Hierarchical Representation with Reinforcement Learning.Ruyi An,Yewen Li,Xu He,Pengjie Gu,Mengchen Zhao,Dong Li,Jianye Hao,Bo An,Chaojie Wang,Mingyuan Zhou.CVPR 2024.
2.Offline RL with discrete proxy representations for generalizability in POMDPs.Pengjie Gu,Xinyu Cai ,Dong Xing,Xinrun Wang*,Mengchen Zhao*,Bo An NeurIPS,2023.
3.Co-speech Gesture Synthesis by Reinforcement Learning with Contrastive Pre-trained Rewards.Mingyang Sun†,Mengchen Zhao†,Yaqing Hou,Minglei Li,Huang Xu,Songcen Xu,Jianye Hao CVPR,2023.
4.RLMixer:A Reinforcement Learning Approach for Integrated Ranking with Contrastive User Preference Modeling.Jing Wang†,Mengchen Zhao†,Wei Xia,Zhenhua Dong,Ruiming Tang,Rui Zhang,Guangyong Chen,Jianye Hao,Phengann Heng PAKDD,2023.
5.Learning Pseudometric Based Action Representations for Offline Reinforcement Learning.Pengjie Gu,Mengchen Zhao*,Chen Chen,Jianye Hao,Bo An ICML,2022.
6.Online Ad Hoc Teamwork Under Partial Observability. Pengjie Gu,Mengchen Zhao*,Jianye Hao,Bo An ICLR,2022.
7.Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation.Yankai Chen,Menglin Yang,Yingxue Zhang,Mengchen Zhao,Ziqiao Meng,Jianye Hao,Irwin King WSDM,2022.
8.Empirical Policy Optimization for n-Player Markov Games. Yuanheng Zhu,Weifan Li,Mengchen Zhao, Jianye Hao,Dongbin Zhao IEEE Transactions on Cybernetics,2022.
9.The ReprGesture entry to the GENEA Challenge 2022. Sicheng Yang,Zhiyong Wu,Minglei Li,Mengchen Zhao, Jiuxin Lin,Liyang Chen, Weihong Bao ICMI,2022.
10.Efficient Dual-Process Cognitive Recommender Balancing Accuracy and Diversity.Yixu Gao,Kun Shao, Zhijian Duan,Zhongyu Wei,Dong Li,Bin Wang,Mengchen Zhao,Jianye Hao DASFAA,2022.
11.CMML:Contextual Modulation Meta Learning for Cold-Start Recommendation.Xidong Feng,Chen Chen, Dong Li,Mengchen Zhao,Jianye Hao,Jun Wang CIKM,2021.
12.Event-Triggered Multi-Agent Reinforcement Learning with Communication under Limited-bandwidth Constraint.Guangzheng Hu.Yuanheng Zhu.Dongbin Zhao.Mengchen Zhao.Jianye Hao IEEE Transactions on Neural Networks and Learning Systems.2021.
13.Securing the Deep Fraud Detector in Large-Scale E-Commerce Platform via Adversarial Machine Learning Approach. Qingyu Guo.Zhao Li,Bo An,Pengrui Hui,Jiaming Huang,Long Zhang,and Mengchen Zhao* WWW,2019.
14.Impression Allocation for Combating Fraud in E-Commerce via Deep Reinforcement Learning with Action Norm Penalty.Mengchen Zhao,Zhao Li,Bo An,Haifeng Lu,Yifan Yang,Chen Chu IJCAI,2018.
15.Data Poisoning Attacks on Multi-task Relationship Learning.Mengchen Zhao,Bo An,Yaodong Yu,Sulin Liu ,Sinno Jialin Pan AAAI,2018.
16.HogRider:Champion Agent of Microsoft Malmo collaborative AI challenge.Yanhai Xiong,Haipeng Chen, Mengchen Zhao,Bo An AAAI,2018.
17.Camera placement based on vehicle traffic for better city security surveillance.Xiaobo Ma,He Yihui ,Mengchen Zhao,Luo Xiapu,Li Jianfeng,Bo An,Xiaohong Guan IEEE Intelligent Systems,2018.
18.Randomized Security Patrolling for Link Flooding Attack Detection.Xiaobo Ma,Yihui He,Xiapu Luo, Jianfeng Li,Mengchen Zhao,Bo An,Xiaohong Guan Transactions on Dependable and Secure Computing.2018.
19.Efficient Label Contamination Attacks Against Black-Box Learning Models.Mengchen Zhao,Bo An,Wei Gao ,Teng Zhang IJCAI,2017.
20.Optimizing Personalized Email Filtering Thresholds to Mitigate Sequential Spear Phishing Attacks. Mengchen Zhao.Bo An.Christopher Kiekintveld AAAI.2016.
21.An Initial Study on Personalized Filtering Thresholds in Defending Sequential Spear Phishing Attacks.Mengchen Zhao,Bo An,Christopher Kiekintveld IJCAI workshop,2015.
