Siyuan Li (李斯源)

About Me

I am currently an Associate Professor in the Faculty of Computing at Harbin Institue of Technology and a member in the Pattern Recognition and Intelligent System Research Center. Previously, I obtained my Ph.D. in computer science under the supervision of Prof. Chongjie Zhang (张崇洁) from the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University. My research interests include Embodied AI and AI for Science.

Publications

2026

• Curriculum Reinforcement Learning with Measurable Task Representation Learning.
  Yongyan Wen, Siyuan Li#, Mingjian Fu, Yiqin Yang, Xun Wang, Peng Liu
  NN 2026: Neural Networks
  
• Adaptive Visual-Tactile Fusion for Contact-Rich Dexterous Manipulation.
  Zedong Cai, Chuan Liu, Siyuan Li, Peng Liu
  RA-L 2026: IEEE ROBOTICS AND AUTOMATION LETTERS
  
• Optimization of power allocation in ultra-dense small cellular networks with information-gain-guided reinforcement learning.
  Mingjian Fu, Zhifei Lin, Fenglin Ni, Siyuan Li, Xinyi Lin, Zhenghong Wang, Guangyong Chen, Yuanlong Yu
  TCE 2026: IEEE Transactions on Consumer Electronics
  
• GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System.
  Yiqin Yang, Xu Yang, Yuhua Jiang, Ni Mu, Hao Hu, Runpeng Xie, Ziyou Zhang, Siyuan Li, Yuan-Hua Ni, Qianchuan Zhao, Bo Xu
  ICLR 2026: The Fourteenth International Conference on Learning Representations
  
• MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios.
  Xuantang Xiong, Ni Mu, Runpeng Xie, Senhao Yang, Yaqing Wang, Lexiang Wang, Yao Luan, Siyuan Li, Shuang Xu, Yiqin Yang, Bo Xu
  AAAI 2026: The Fortieth AAAI Conference on Artificial Intelligence
  

2025

• Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning.
  Siyuan Li, Feifan Liu, Lingfei Cui, Jiani Lu, Qinqin Xiao, Xirui Yang, Peng Liu, Kewu Sun#, Zhe Ma, Xun Wang
  AAAI 2025: The Thirty-Ninth AAAI Conference on Artificial Intelligence
  
• SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks.
  Yongyan Wen, Siyuan Li#, Rongchang Zuo, Lei Yuan, Hangyu Mao, Peng Liu
  AAAI 2025: The Thirty-Ninth AAAI Conference on Artificial Intelligence
  
• Auxiliary Reward Generation with Transition Distance Representation Learning.
  Siyuan Li, Shijie Han, Yingnan Zhao, Yiqin Yang, Qianchuan Zhao, Peng Liu
  T-ASE 2025: IEEE Transactions on Automation Science and Engineering
  
• An Imitative Reinforcement Learning Framework for Pursuit-Lock-Launch Missions.
  Siyuan Li#, Rongchang Zuo, Bofei Liu, Yaoyu He, Peng Liu, Yingnan Zhao
  TAAS 2025: ACM Transactions on Autonomous and Adaptive Systems
  

2024

• Robust Visual Imitation Learning with Inverse Dynamics Representations.
  Siyuan Li*, Xun Wang*, Rongchang Zuo, Kewu Sun, Lingfei Cui, Jishiyu Ding, Peng Liu, Zhe Ma
  AAAI 2024: The Thirty-Eighth AAAI Conference on Artificial Intelligence
  PDF
• IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making.
  Hui Niu*, Siyuan Li*, Jiahao Zheng, Zhouchi Lin, Bo An, Jian Li, Jian Guo
  IJCAI 2024: The Thirty-Third International Joint Conference on Artificial Intelligence
  
• MacMic: Executing Iceberg Orders via Hierarchical Reinforcement Learning.
  Hui Niu*, Siyuan Li*, Jian Li
  IJCAI 2024: The Thirty-Third International Joint Conference on Artificial Intelligence
  
• A Multi-Agent Learning Framework for Mixed-Integer Linear Programming.
  Yuchen Jing, Binyan Liang, Siyuan Li#, Feifan Liu, Wei Zhao, Peng Liu
  INFOR 2024 (JCR-Q1): Information Systems and Operational Research
  
• Joint Learning of Volume Scheduling and Order Placement Policies for Optimal Order Execution.
  Siyuan Li, Hui Niu, Jiani Lu, Peng Liu
  Mathematics 2024 (JCR-Q1)
  
• Toward Automatic Market Making: An Imitative Reinforcement Learing Approach with Predictive Representation Learning.
  Siyuan Li, Yafei Chen, Hui Niu, Jiahao Zheng, Zhouchi Lin, Jian Li, Jian Guo, Zhen Wang
  TETCI 2024 (JCR-Q1): IEEE Transactions on Emerging Topics in Computational Intelligence
  

2023

• IOB: integrating optimization transfer and behavior transfer for multi‑policy reuse.
  Siyuan Li, Hao Li, Jin Zhang, Zhen Wang, Peng Liu, Chongjie Zhang
  JAAMAS 2023: Autonomous Agents and Multi-Agent Systems
  PDF
• Learning to Solve Tasks with Exploring Prior Behaviours.
  Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang, Oya Celiktutan
  IROS 2023: The 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems
  PDF
• Classifying Ambiguous Identities in Stochastic Games with Multi-Agent Reinforcement Learning.
  Shijie Han, Siyuan Li#, Bo An, Wei Zhao, Peng Liu
  JAAMAS 2023: Autonomous Agents and Multi-Agent Systems
  PDF
• Behavior Contrastive Learning for Unsupervised Skill Discovery.
  Rushuai Yang, Chenjia Bai, Hongyi Guo, Siyuan Li, Bin Zhao, Zhen Wang, Peng Liu, Xuelong Li
  ICML 2023: International Conference on Machine Learning
  PDF
• Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery.
  Yiqin Yang, Hao Hu, Wenzhe Li, Siyuan Li, Jun Yang, Qianchuan Zhao, Chongjie Zhang
  AAAI 2023: The Thirty-Seventh AAAI Conference on Artificial Intelligence
  PDF

2022 and Before

• CUP: Critic-Guided Policy Reuse.
  Jin Zhang, Siyuan Li, Chongjie Zhang
  NeurIPS 2022 (Spotlight): Advances in Neural Information Processing Systems
  PDF | Code
• MetaTrader: A Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization.
  Hui Niu*, Siyuan Li*, Jian Li
  CIKM 2022: The 31st ACM International Conference on Information and Knowledge Management
  PDF
• Active Hierarchical Exploration with Stable Subgoal Representation Learning.
  Siyuan Li, Jin Zhang, Jianhao Wang, Yang Yu, Chongjie Zhang
  ICLR 2022: The Tenth International Conference on Learning Representations
  PDF | Video | Code
• Offline Reinforcement Learning with Reverse Model-based Imagination.
  Jianhao Wang, Wenzhe Li, Haozhe Jiang, Guangxiang Zhu, Siyuan Li, Chongjie Zhang
  NeurIPS 2021: Advances in Neural Information Processing Systems
  PDF | Video | Code
• Learning Subgoal Representations with Slow Dynamics.
  Siyuan Li*, Lulu Zheng*, Jianhao Wang, Chongjie Zhang
  ICLR 2021: The Ninth International Conference on Learning Representations
  PDF | Video | Code
• Deep Reinforcement Learning with Hierarchical Structures.
  Siyuan Li
  IJCAI DC 2021: The Thirtieth International Joint Conference on Artificial Intelligence Doctoral Consortium
  PDF
• Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards.
  Siyuan Li*, Rui Wang*, Minxue Tang, Chongjie Zhang
  NeurIPS 2019: Advances in Neural Information Processing Systems
  PDF | Video | Code
• Context-Aware Policy Reuse.
  Siyuan Li, Fangda Gu, Guangxiang Zhu, Chongjie Zhang
  AAMAS 2019 (Oral): International Conference on Autonomous Agents and MultiAgent Systems
  PDF | Code
• An Optimal Online Method of Selecting Source Policies for Reinforcement Learning.
  Siyuan Li, Chongjie Zhang
  AAAI 2018 (Spotlight): The Thirty-Second AAAI Conference on Artificial Intelligence
  PDF

Education

• Ph.D. in Computer Science
  IIIS, Tsinghua University @ Beijing, China, 2017 -- 2022
  Deep Reinforcement Learning
• B.Sc. in Telecommunication Engineering
  Beijing University of Post and Telecommunications @ Beijing, China, 2013 -- 2017