Profile
I am an AI researcher working at the intersection of reinforcement learning, language-model alignment, and agent safety. I am interested in how systems learn from feedback, where objectives break down, and how to evaluate and improve reliability in open-ended environments.
01
Research interests
Reinforcement LearningLLM SafetyAlignmentAgent SafetyWorld Models
02
Experience
Current
AI Research Intern
BAAI & Peking University AI Lab
Research on reinforcement learning, language-model safety, alignment, and agent behavior.
Previously
Systems Researcher
Chinese Academy of Sciences
C++ compiler and operator-generation systems for specialized graph-computing hardware.
03
Education
Undergraduate
Computer Science
China University of Mining and Technology, Beijing
04
Technical toolkit
PyTorchTransformersCUDAvLLMRayDockerLinuxC / C++
05
Selected publications
Publication details are being updated.
CURRICULUM VITAE
CV link will appear here when configured.