Personal Profile

Assistant Professor, Recipient of the National Excellent Young Scientists Fund. His research focuses on intelligent perception and decision-making in open environments. He has published over 30 first-authored or corresponding-authored papers in top journals such asIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)andInternational Journal of Computer Vision (IJCV), as well as at leading international conferences including NeurIPS and CVPR. He has undertaken more than ten national and provincial-level research projects, with multiple achievements successfully applied in important military and civilian scenarios. He has been awarded the First Prize of Science and Technology Progress by the China Electronics Society (2022), the Special Prize of Science and Technology Progress of Guangdong Province (2023), and the First Prize of Science and Technology Progress by the Chinese Association for Command and Control (2024).

Specific Research Directions

1. Reinforcement Learning + X: Exploring efficient and large-scale reinforcement learning algorithms and their applications, including RL + large models, RL + Science, RL + representation learning, world models, and multi-agent learning.

2. 3D Modeling and Prediction for Open Scenarios

3. Brain-inspired Perception and Computing for Intelligent Robots

Representative Papers & Projects

Representative Papers：

https://scholar.google.com.tw/citations?hl=zh-CN&user=CFMuFGoAAAAJ

Representative Projects：

• Youth Project of the National Natural Science Foundation of China: Pedestrian Detection and Re-identification in Multi-Camera Surveillance Networks (Principal Investigator).

• General Program of the National Natural Science Foundation of China: Research on Spiking Reinforcement Learning for Event-based Data (Principal Investigator).

• Excellent Young Scientists Fund Project of the National Natural Science Foundation of China: Intelligent Game in Open Environments (Principal Investigator).

• Key-Area Research and Development Program of Guangdong Province: "Research and Application of Key Technologies for Imperfect Information Game Decision-Making Driven by Ultra-Large-Scale AI Computing Power" – Subject "Key Technologies for Autonomous Learning and Evolution of Game Decision-Making Agents" (Principal Investigator).

• ***Project: "***Swarm Reinforcement Game" (Principal Investigator).

• ***Project: "***Swarm Evolutionary Game" (Principal Investigator).

Welcome to Apply

• Solid mathematical foundation and programming skills, rich experience in deep learning, and rigorous logical reasoning ability.

• The ability to conduct in-depth problem analysis, courage to put forward viewpoints, and strong execution.

• Great enthusiasm for scientific research, high self-drive, and proactive attitude.

• For doctoral candidates under the assessment system: Priority will be given to those who have published first-authored papers (as sole first author or first among co-first authors) in CCF-A conferences (including ECCV, ICLR) or CCF-B (or higher) journals; exceptionally outstanding candidates are exempted from this requirement.