Publications

2026

1. ACL

   MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement.

   ZhenChun Xu ,  Yi Cai ,  Dajun Zheng ,  yuan ,  Mengchen Zhao ,  Qixiang Wang ,  and  Jiexin Wang

   In The 64th Annual Meeting of the Association for Computational Linguistics , 2026

   Bib

   @inproceedings{MavenCoder,
     title = {MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement.},
     author = {Xu, ZhenChun and Cai, Yi and Zheng, Dajun and li yuan and Zhao, Mengchen and Wang, Qixiang and Wang, Jiexin},
     year = {2026},
     booktitle = {The 64th Annual Meeting of the Association for Computational Linguistics},
   }

2. ACL

   SeDev: Structured Semantic Exploration for LLM-Driven Code Generation.

   Ronghui Yang ,  Jie Liu ,  Jiajie Zeng ,  Jiexin Wang ,  Jiuchuan Jiang ,  Bo An ,  Yi Cai ,  and  Mengchen Zhao*

   In The 64th Annual Meeting of the Association for Computational Linguistics , 2026

   Bib

   @inproceedings{SeDev,
     title = {SeDev: Structured Semantic Exploration for LLM-Driven Code Generation.},
     author = {Yang, Ronghui and Liu, Jie and Zeng, Jiajie and Wang, Jiexin and Jiang, Jiuchuan and An, Bo and Cai, Yi and Zhao{*}, Mengchen},
     year = {2026},
     booktitle = {The 64th Annual Meeting of the Association for Computational Linguistics},
   }

3. ACL

   Unlocking Human-Like Visible Logic: How Logic Diagrams Boost Logic Reasoning in Large Language Models?

   Xin Wu ,  Yuqi Bu ,  Mengchen Zhao ,  Qingbao Huang ,  and  Yi Cai

   In The 63rd Annual Meeting of the Association for Computational Linguistics , 2026

   Bib

   @inproceedings{visible_logic,
     title = {Unlocking Human-Like Visible Logic: How Logic Diagrams Boost Logic Reasoning in Large Language Models?},
     author = {Wu, Xin and Bu, Yuqi and Zhao, Mengchen and Huang, Qingbao and Cai, Yi},
     year = {2026},
     booktitle = {The 63rd Annual Meeting of the Association for Computational Linguistics},
   }

4. AAAI

   PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork.

   Hohei Chan ,  Xinzhi Zhang ,  Antao Xiang ,  Weinan Zhang ,  and  Mengchen Zhao*

   In Proceedings of The 40th AAAI Conference on Artificial Intelligence , 2026

   Bib PDF

   @inproceedings{padiff,
     title = {PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork.},
     author = {Chan, Hohei and Zhang, Xinzhi and Xiang, Antao and Zhang, Weinan and Zhao{*}, Mengchen},
     year = {2026},
     booktitle = {Proceedings of The 40th AAAI Conference on Artificial Intelligence},
   }

2025

1. NeurIPS

   MTRec: Learning to Align with User Preferences via Mental Reward Models.

   Mengchen Zhao ,  Yifan Gao ,  Yaqing Hou ,  Xiangyang Li ,  Pengjie Gu ,  Zhenhua Dong ,  Ruiming Tang ,  and  Yi Cai

   In Proceedings of the 39th Advances in Neural Information Processing Systems , 2025

   Bib PDF

   @inproceedings{mtrec,
     title = {MTRec: Learning to Align with User Preferences via Mental Reward Models.},
     author = {Zhao, Mengchen and Gao, Yifan and Hou, Yaqing and Li, Xiangyang and Gu, Pengjie and Dong, Zhenhua and Tang, Ruiming and Cai, Yi},
     year = {2025},
     booktitle = {Proceedings of the 39th Advances in Neural Information Processing Systems},
   }

2. DAI

   Efficient Decision Sequence Modeling via Feature-Level Masking.

   Xinzhi Zhang ,  Yifan Gao ,  Yaqing Hou ,  Xuechuan Liu ,  Zengyang Wang ,  Yi Cai ,  Bo An ,  and  Mengchen Zhao*

   In Proceedings of the 7th International Conference on Distributed Artificial Intelligence , 2025

   Bib PDF

   @inproceedings{DEDS,
     title = {Efficient Decision Sequence Modeling via Feature-Level Masking.},
     author = {Zhang, Xinzhi and Gao, Yifan and Hou, Yaqing and Liu, Xuechuan and Wang, Zengyang and Cai, Yi and An, Bo and Zhao{*}, Mengchen},
     year = {2025},
     booktitle = {Proceedings of the 7th International Conference on Distributed Artificial Intelligence},
   }

3. ECAI

   DiTAC: Discrete Teamwork Abstraction for Ad Hoc Collaboration.

   Jing Wang ,  Pengjie Gu ,  Mengchen Zhao* ,  Guangyong Chen ,  Furui Liu ,  and  Pheng-Ann Heng

   In Proceedings of the 28th European Conference on Artificial Intelligence , 2025

   Bib PDF

   @inproceedings{DiTac,
     title = {DiTAC: Discrete Teamwork Abstraction for Ad Hoc Collaboration.},
     author = {Wang, Jing and Gu, Pengjie and Zhao{*}, Mengchen and Chen, Guangyong and Liu, Furui and Heng, Pheng-Ann},
     year = {2025},
     booktitle = {Proceedings of the 28th European Conference on Artificial Intelligence},
   }

4. ACL

   RTADev: Intention Aligned Multi-Agent Framework for Software Development.

   Jie Liu ,  Guohua Wang ,  Ronghui Yang ,  Jiajie Zeng ,  Mengchen Zhao* ,  and  Yi Cai

   In Findings of the 63rd Annual Meeting of the Association for Computational Linguistics , 2025

   Bib PDF

   @inproceedings{rtadev,
     title = {RTADev: Intention Aligned Multi-Agent Framework for Software Development.},
     author = {Liu, Jie and Wang, Guohua and Yang, Ronghui and Zeng, Jiajie and Zhao{*}, Mengchen and Cai, Yi},
     year = {2025},
     booktitle = {Findings of the 63rd Annual Meeting of the Association for Computational Linguistics},
   }

5. ICML

   Ad Hoc Teamwork via Offline Goal-Based Decision Transformers.

   Xinzhi Zhang ,  Hohei Chan ,  Deheng Ye ,  Yi Cai ,  and  Mengchen Zhao*

   In Proceedings of the 42nd International Conference on Machine Learning , 2025

   Bib PDF

   @inproceedings{taget,
     title = {Ad Hoc Teamwork via Offline Goal-Based Decision Transformers.},
     author = {Zhang, Xinzhi and Chan, Hohei and Ye, Deheng and Cai, Yi and Zhao{*}, Mengchen},
     year = {2025},
     booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
   }

2024

1. TOIS

   A Unified Framework for Multi-Domain CTR Prediction via Large Language Models.

   Zichuan Fu ,  Xiangyang Li ,  Chuhan Wu ,  Yichao Wang ,  Kuicai Dong ,  Xiangyu Zhao ,  Mengchen Zhao ,  Huifeng Guo ,  and  Ruiming Tang

   ACM Transactions on Information Systems, 2024

   Bib PDF

   @article{unictr,
     title = {A Unified Framework for Multi-Domain CTR Prediction via Large Language Models.},
     author = {Fu, Zichuan and Li, Xiangyang and Wu, Chuhan and Wang, Yichao and Dong, Kuicai and Zhao, Xiangyu and Zhao, Mengchen and Guo, Huifeng and Tang, Ruiming},
     year = {2024},
     journal = {ACM Transactions on Information Systems},
   }

2. IJCAI

   PoRank: A Practical Framework for Learning to Rank Policies.

   Pengjie Gu ,  Mengchen Zhao* ,  Xu He ,  Yi Cai ,  and  Bo An

   In Proceedings of the 33rd International Joint Conference on Artificial Intelligence , 2024

   Bib PDF

   @inproceedings{porank,
     title = {PoRank: A Practical Framework for Learning to Rank Policies.},
     author = {Gu, Pengjie and Zhao{*}, Mengchen and He, Xu and Cai, Yi and An, Bo},
     year = {2024},
     booktitle = {Proceedings of the 33rd International Joint Conference on Artificial Intelligence},
   }

3. CVPR

   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 ,  and  Mingyuan Zhou

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2024

   Bib PDF

   @inproceedings{vae,
     title = {Improving Unsupervised Hierarchical Representation with Reinforcement Learning.},
     author = {An, Ruyi and Li, Yewen and He, Xu and Gu, Pengjie and Zhao, Mengchen and Li, Dong and Hao, Jianye and An, Bo and Wang, Chaojie and Zhou, Mingyuan},
     year = {2024},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   }

2023

1. NeurIPS

   Offline RL with Discrete Proxy Representations for Generalizability in POMDPs.

   Pengjie Gu ,  Xinyu Cai ,  Dong Xing ,  Xinrun Wang* ,  Mengchen Zhao* ,  and  Bo An

   In Proceedings of the 37th Conference on Neural Information Processing Systems , 2023

   Bib PDF

   @inproceedings{pomdp,
     title = {Offline RL with Discrete Proxy Representations for Generalizability in POMDPs.},
     author = {Gu, Pengjie and Cai, Xinyu and Xing, Dong and Wang{*}, Xinrun and Zhao{*}, Mengchen and An, Bo},
     year = {2023},
     booktitle = {Proceedings of the 37th Conference on Neural Information Processing Systems},
   }

2. PAKDD

   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 ,  and  Phengann Heng

   In Proceedings of the 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining , 2023

   Bib PDF

   @inproceedings{RLMixer,
     title = {RLMixer: A Reinforcement Learning Approach for Integrated Ranking with Contrastive User Preference Modeling.},
     author = {Wang{†}, Jing and Zhao{†}, Mengchen and Xia, Wei and Dong, Zhenhua and Tang, Ruiming and Zhang, Rui and Chen, Guangyong and Hao, Jianye and Heng, Phengann},
     year = {2023},
     booktitle = {Proceedings of the 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
   }

3. CVPR

   Co-speech Gesture Synthesis by Reinforcement Learning with Contrastive Pre-trained Rewards.

   Mingyang Sun† ,  Mengchen Zhao† ,  Yaqing Hou ,  Minglei Li ,  Huang Xu ,  Songcen Xu ,  and  Jianye Hao

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023

   Bib PDF

   @inproceedings{racer,
     title = {Co-speech Gesture Synthesis by Reinforcement Learning with Contrastive Pre-trained Rewards.},
     author = {Sun{†}, Mingyang and Zhao{†}, Mengchen and Hou, Yaqing and Li, Minglei and Xu, Huang and Xu, Songcen and Hao, Jianye},
     year = {2023},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   }

2022

1. ICML

   Learning Pseudometric Based Action Representations for Offline Reinforcement Learning.

   Pengjie Gu ,  Mengchen Zhao* ,  Chen Chen ,  Jianye Hao ,  and  Bo An

   In Proceedings of the 39th International Conference on Machine Learning , 2022

   Bib PDF

   @inproceedings{MERLION,
     title = {Learning Pseudometric Based Action Representations for Offline Reinforcement Learning.},
     author = {Gu, Pengjie and Zhao{*}, Mengchen and Chen, Chen and Hao, Jianye and An, Bo},
     year = {2022},
     booktitle = {Proceedings of the 39th International Conference on Machine Learning},
   }

2. ICLR

   Online Ad Hoc Teamwork Under Partial Observability.

   Pengjie Gu ,  Mengchen Zhao* ,  Jianye Hao ,  and  Bo An

   In International Conference on Learning Representations , 2022

   Bib PDF

   @inproceedings{ODITS,
     title = {Online Ad Hoc Teamwork Under Partial Observability.},
     author = {Gu, Pengjie and Zhao{*}, Mengchen and Hao, Jianye and An, Bo},
     year = {2022},
     booktitle = {International Conference on Learning Representations},
   }

3. WSDM

   Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation.

   Yankai Chen ,  Menglin Yang ,  Yingxue Zhang ,  Mengchen Zhao ,  Ziqiao Meng ,  Jianye Hao ,  and  Irwin King

   In Proceedings of the 15th ACM International Conference on Web Search and Data Mining , 2022

   Bib PDF

   @inproceedings{HyperKGR,
     title = {Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation.},
     author = {Chen, Yankai and Yang, Menglin and Zhang, Yingxue and Zhao, Mengchen and Meng, Ziqiao and Hao, Jianye and King, Irwin},
     year = {2022},
     booktitle = {Proceedings of the 15th ACM International Conference on Web Search and Data Mining},
   }

4. TOC

   Empirical Policy Optimization for n-Player Markov Games.

   Yuanheng Zhu ,  Weifan Li ,  Mengchen Zhao ,  Jianye Hao ,  and  Dongbin Zhao

   IEEE Transactions on Cybernetics, 2022

   Bib PDF

   @article{EPO,
     title = {Empirical Policy Optimization for n-Player Markov Games.},
     author = {Zhu, Yuanheng and Li, Weifan and Zhao, Mengchen and Hao, Jianye and Zhao, Dongbin},
     journal = {IEEE Transactions on Cybernetics},
     year = {2022},
   }

5. ICMI

   The ReprGesture entry to the GENEA Challenge 2022.

   Sicheng Yang ,  Zhiyong Wu ,  Minglei Li ,  Mengchen Zhao ,  Jiuxin Lin ,  Liyang Chen ,  and  Weihong Bao

   In Proceedings of the 2022 International Conference on Multimodal Interaction , 2022

   Bib PDF

   @inproceedings{GENEA,
     title = {The ReprGesture entry to the GENEA Challenge 2022.},
     author = {Yang, Sicheng and Wu, Zhiyong and Li, Minglei and Zhao, Mengchen and Lin, Jiuxin and Chen, Liyang and Bao, Weihong},
     year = {2022},
     booktitle = {Proceedings of the 2022 International Conference on Multimodal Interaction},
   }

6. DASFAA

   Efficient Dual-Process Cognitive Recommender Balancing Accuracy and Diversity.

   Yixu Gao ,  Kun Shao ,  Zhijian Duan ,  Zhongyu Wei ,  Dong Li ,  Bin Wang ,  Mengchen Zhao ,  and  Jianye Hao

   In International Conference on Database Systems for Advanced Applications , 2022

   Bib PDF

   @inproceedings{DASFAA,
     title = {Efficient Dual-Process Cognitive Recommender Balancing Accuracy and Diversity.},
     author = {Gao, Yixu and Shao, Kun and Duan, Zhijian and Wei, Zhongyu and Li, Dong and Wang, Bin and Zhao, Mengchen and Hao, Jianye},
     year = {2022},
     booktitle = {International Conference on Database Systems for Advanced Applications},
   }

7. CIKM

   CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation.

   Xidong Feng ,  Chen Chen ,  Dong Li ,  Mengchen Zhao ,  Jianye Hao ,  and  Jun Wang

   In Proceedings of the 30th ACM International Conference on Information and Knowledge Management , 2022

   Bib PDF

   @inproceedings{CMML,
     title = {CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation.},
     author = {Feng, Xidong and Chen, Chen and Li, Dong and Zhao, Mengchen and Hao, Jianye and Wang, Jun},
     year = {2022},
     booktitle = {Proceedings of the 30th ACM International Conference on Information and Knowledge Management},
   }

2021

1. TNNLS

   Event-Triggered Multi-Agent Reinforcement Learning with Communication under Limited-bandwidth Constraint.

   Guangzheng Hu ,  Yuanheng Zhu ,  Dongbin Zhao ,  Mengchen Zhao ,  and  Jianye Hao

   IEEE Transactions on Neural Networks and Learning Systems, 2021

   Bib PDF

   @article{communication,
     title = {Event-Triggered Multi-Agent Reinforcement Learning with Communication under Limited-bandwidth Constraint.},
     author = {Hu, Guangzheng and Zhu, Yuanheng and Zhao, Dongbin and Zhao, Mengchen and Hao, Jianye},
     year = {2021},
     journal = {IEEE Transactions on Neural Networks and Learning Systems},
   }

2019

1. WWW

   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*

   In Proceedings of the World Wide Web Conference , 2019

   Bib PDF

   @inproceedings{secure,
     title = {Securing the Deep Fraud Detector in Large-Scale E-Commerce Platform via Adversarial Machine Learning Approach.},
     author = {Guo, Qingyu and Li, Zhao and An, Bo and Hui, Pengrui and Huang, Jiaming and Zhang, Long and Zhao{*}, Mengchen},
     year = {2019},
     booktitle = {Proceedings of the World Wide Web Conference},
   }

2018

1. IJCAI

   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 ,  and  Chen Chu

   In Proceedings of the 27th International Joint Conference on Artificial Intelligence , 2018

   Bib PDF

   @inproceedings{impression,
     title = {Impression Allocation for Combating Fraud in E-Commerce via Deep Reinforcement Learning with Action Norm Penalty.},
     author = {Zhao, Mengchen and Li, Zhao and An, Bo and Lu, Haifeng and Yang, Yifan and Chu, Chen},
     year = {2018},
     booktitle = {Proceedings of the 27th International Joint Conference on Artificial Intelligence},
   }

2. AAAI

   Data Poisoning Attacks on Multi-task Relationship Learning.

   Mengchen Zhao ,  Bo An ,  Yaodong Yu ,  Sulin Liu ,  and  Sinno Jialin Pan

   In Proceedings of the 32nd AAAI Conference on Artificial Intelligence , 2018

   Bib PDF

   @inproceedings{poison,
     title = {Data Poisoning Attacks on Multi-task Relationship Learning.},
     author = {Zhao, Mengchen and An, Bo and Yu, Yaodong and Liu, Sulin and Pan, Sinno Jialin},
     year = {2018},
     booktitle = {Proceedings of the 32nd AAAI Conference on Artificial Intelligence},
   }

3. AAAI

   HogRider: Champion Agent of Microsoft Malmo collaborative AI challenge.

   Yanhai Xiong ,  Haipeng Chen ,  Mengchen Zhao ,  and  Bo An

   In Proceedings of the 32nd AAAI Conference on Artificial Intelligence , 2018

   Bib PDF

   @inproceedings{hogrider,
     title = {HogRider: Champion Agent of Microsoft Malmo collaborative AI challenge.},
     author = {Xiong, Yanhai and Chen, Haipeng and Zhao, Mengchen and An, Bo},
     year = {2018},
     booktitle = {Proceedings of the 32nd AAAI Conference on Artificial Intelligence},
   }

4. IS

   Camera placement based on vehicle traffic for better city security surveillance.

   Xiaobo Ma ,  He Yihui ,  Mengchen Zhao ,  Luo Xiapu ,  Li Jianfeng ,  Bo An ,  and  Xiaohong Guan

   IEEE Intelligent Systems, 2018

   Bib PDF

   @article{camera,
     title = {Camera placement based on vehicle traffic for better city security surveillance.},
     author = {Ma, Xiaobo and Yihui, He and Zhao, Mengchen and Xiapu, Luo and Jianfeng, Li and An, Bo and Guan, Xiaohong},
     year = {2018},
     journal = {IEEE Intelligent Systems},
   }

5. TDSC

   Randomized Security Patrolling for Link Flooding Attack Detection.

   Xiaobo Ma ,  Yihui He ,  Xiapu Luo ,  Jianfeng Li ,  Mengchen Zhao ,  Bo An ,  and  Xiaohong Guan

   Transactions on Dependable and Secure Computing, 2018

   Bib PDF

   @article{link,
     title = {Randomized Security Patrolling for Link Flooding Attack Detection.},
     author = {Ma, Xiaobo and He, Yihui and Luo, Xiapu and Li, Jianfeng and Zhao, Mengchen and An, Bo and Guan, Xiaohong},
     year = {2018},
     journal = {Transactions on Dependable and Secure Computing},
   }

2017

1. IJCAI

   Efficient Label Contamination Attacks Against Black-Box Learning Models.

   Mengchen Zhao ,  Bo An ,  Wei Gao ,  and  Teng Zhang

   In Proceedings of the 26th International Joint Conference on Artificial Intelligence , 2017

   Bib PDF

   @inproceedings{label,
     title = {Efficient Label Contamination Attacks Against Black-Box Learning Models.},
     author = {Zhao, Mengchen and An, Bo and Gao, Wei and Zhang, Teng},
     year = {2017},
     booktitle = {Proceedings of the 26th International Joint Conference on Artificial Intelligence},
   }

2016

1. AAAI

   Optimizing Personalized Email Filtering Thresholds to Mitigate Sequential Spear Phishing Attacks.

   Mengchen Zhao ,  Bo An ,  and  Christopher Kiekintveld

   In Proceedings of the 30th AAAI Conference on Artificial Intelligence , 2016

   Bib PDF

   @inproceedings{filtering,
     title = {Optimizing Personalized Email Filtering Thresholds to Mitigate Sequential Spear Phishing Attacks.},
     author = {Zhao, Mengchen and An, Bo and Kiekintveld, Christopher},
     year = {2016},
     booktitle = {Proceedings of the 30th AAAI Conference on Artificial Intelligence},
   }

2015

1. IJCAI

   An Initial Study on Personalized Filtering Thresholds in Defending Sequential Spear Phishing Attacks.

   Mengchen Zhao ,  Bo An ,  and  Christopher Kiekintveld

   In Proceedings of the IJCAI Workshop on Behavioral, Economic and Computational Intelligence for Security , 2015

   Bib PDF

   @inproceedings{email,
     title = {An Initial Study on Personalized Filtering Thresholds in Defending Sequential Spear Phishing Attacks.},
     author = {Zhao, Mengchen and An, Bo and Kiekintveld, Christopher},
     year = {2015},
     booktitle = {Proceedings of the IJCAI Workshop on Behavioral, Economic and Computational Intelligence for Security},
   }