I am a Ph.D. candidate in School of Intelligence Science and Technology at Peking University (PKU), advised by Prof. Yitao Liang. Before joining PKU, I received my MSc and BA degrees in Control Science and Technology from Beijing Institute of Technology. I work on building open-ended embodied agents with multi-task skills, including visual localization, task planning and decision making.
In particular, I am interested in leveraging large pre-trained Foundation Models to improve generalization of agent capabilities.

🔥 News

• 2023.03:  🎉🎉 Two papers are accepted by the IEEE Computer Vision and Patter Recognition (CVPR) 2023.

• 2023.02:  🎉🎉 New preprint on generalist open-world planning in Minecraft is available.

• 2023.01:  🎉🎉 New preprint on generalist open-world control in Minecraft is available.

📝 Publications

• Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

  TLDR: We propose a novel interactive planning approach using LLMs that brings a planning-based agent to the apex of Minecraft (an open-world environment) for the first time.

  Zihao Wang, Shaofei Cai, Anji Liu, Xiaojian Ma, Yitao Liang

  arXiv preprint | Paper | Code

• Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

  Shaofei Cai, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang

  CVPR 2023 | Paper | Code

• Graph-Based Contrastive Learning for Description and Detection of Local Features

  Zihao Wang, Zhen Li, Xueyi Li, Wenjie Chen, Xiangdong Liu

  Trans. on Neural Networks and Learning Systems | Paper

• Local Representation is NOT Enough: Soft Point-wise Transformer for descriptor and Detector of Local Features

  Zihao Wang, Xueyi Li, Zhen Li

  IJCAI 2021 | Paper

💬 Invited Talks

• 2023.03, Invited talk at City University of Hong Kong and The Hong Kong Polytechnic University on “open-ended embodied agents with multi-task skills”
• 2022.08, Invited talk at Beijing Institute of General Artificial Intelligence on “learning detection and description of local features”.

🔭 Academic Service

• Reviewer for ICML

💻 Internships

• 2021.05 - 2021.08, Alibaba, Beijing.

📖 Educations

• 2022.09 - now, PhD candidate of Computer Science, Peking University
• 2019.09 - 2022.06, Master of Control Science and Technology, Beijing Institute of Technology
• 2015.09 - 2019.06, Bachlor of Automation, Beijing Institute of Technology

🎖 Honors and Awards

• 2021.10 Chinese National Scholarship
• 2019.06 Outstanding Graduate of Beijing
• 2018.11 Autonomy Prize of Indoor Event on 10th International Micro Air Vehicle Competition and Conference, Melbourne.
• 2018.08 First Prize on China National Robot Competition 2018.
• 2018.04 Meritorious Winner on American Mathematical Contest In Modeling (MCM) 2018.