👨‍🎓 About Me

I am currently a Ph.D. student at Institute of Automation, Chinese Academy of Sciences, advised by Prof. Zeng-Guang Hou and Prof. Guotao Li. My research interests include human-robot interaction, reinforcement learning, and preference learning. My research will focus on Cobodied AI, which aims to achieve profound alignment between robots and humans in complex environments. Specifically, the goal of my research is to ensure that exoskeleton robots can provide efficient assistance across diverse environments for different individuals.

🔥 News

• [2026.02] Two papers (DOMAIN, LEASE) are accepted by IEEE TSMC.
• [2025.05] One paper (WMDD) is accepted by IEEE TCYB.
• [2024.04] One paper (MICRO) is accepted by IJCAI 2024.

📝 Publications

Preprints

• Xiao-Yin Liu, Guotao Li$^*$, Long Sun, Xu Liang, Zeng-Guang Hou$^*$, “ExoTraj: A general lower-limb exoskeleton assistance policy for complex environments”, arxiv preprint, 2026. [Project Page]
• Xiao-Yin Liu, Guotao Li$^*$, Weiqun Wang, Zeng-Guang Hou$^*$, “Personalized lower-limb exoskeleton assistance via preference-based Bayesian optimization”, arxiv preprint, 2026. [Movie]
• Xiao-Yin Liu, Guotao Li$^*$, Weiqun Wang, Zeng-Guang Hou$^*$, “Assistance torque estimation via dynamics-aware optimization for lower-limb exoskeleton in complex environments”, arxiv preprint, 2026. [Movie]

Journals

• Xiao-Yin Liu, Guotao Li$^*$, Xiao-Hu Zhou, Zeng-Guang Hou$^*$, “LEASE: Offline preference-based reinforcement learning with high sample efficiency”, IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC), 2026.[Code]
• Xiao-Yin Liu, Xiao-Hu Zhou$^*$, Mei-Jiang Gui, Guotao Li, Zeng-Guang Hou$^*$ et al., “DOMAIN: Mildly conservative model-based offline reinforcement learning”, IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC), 2025.
• Xiao-Yin Liu, Guotao Li$^*$, Xiao-Hu Zhou, Xu Liang, Zeng-Guang Hou$^*$, “A weight-aware-based multi-source unsupervised domain adaptation method for human motion intention recognition”, IEEE Transactions on Cybernetics (TCYB), 2025. [Code]

Conferences

• Xiao-Yin Liu, Xiao-Hu Zhou$^*$, Guotao Li, Hao Li, Zeng-Guang Hou$^*$ et al., “MICRO: Model-based offline reinforcement learning with a conservative bellman operator”, the 33th International Joint Conference on Artificial Intelligence (IJCAI), 2024. [Code]

🎖 Honors and Awards

Academic Awards

• [2025.12] Doctoral Special Project under the Youth Science and Technology Talent Development Program.
• [2025.06] The 5rd Direct Ph.D. Pilot Program of the Institute of Automation (1/11).
• [2023.03] Technology Star of China University of Petroleum (East China) (1/10).
• [2022.05] Outstanding Student of Shandong Province (0.5%).

Scholarships & Competitions

• [2026.10] BYD Scholarship (1/2, Institute of Automation).
• [2025.08] International Invention Exhibition Gold Award and Macao Foundation Invention Award (0.4%).
• [2019-2023] China National Scholarship for Undergraduate Students (2020, 2021 and 2022).
• [2021.11] First Prize in the China Undergraduate Mathematical Contest in Modeling (0.7%).

📖 Educations

• 2023.09 - Present, Ph.D. candidate, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
• 2019.09 - 2023.06, Undergraduate, Department of Automation, China University of Petroleum (East China), Qingdao, China.

👥 Services

Reviewer for Journals (IEEE TRO, IEEE TCYB, IEEE TCSVT) and Conferences (ICLR, ICRA).