Zefu Lin

Zefu Lin (林泽夫)

Ph.D. Student · Embodied Intelligence, World Models & VLA

Nanjing University
Previously: UCAS / CASIA, CRIPAC

Embodied AI World Models VLA Systems

About Me

I am a Ph.D. student at Nanjing University. I received my M.S. degree in Artificial Intelligence from the University of Chinese Academy of Sciences (UCAS), where I was affiliated with the Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA). My research focuses on embodied intelligence — building agents that perceive, reason, and act in the physical world. I am particularly interested in world models for long-horizon prediction and planning, and vision–language–action (VLA) systems that connect perception, language, and control for generalizable robot behavior.

What's New
Jan 2026 EmbodiedCoder accepted as an Oral at ICRA 2026.
Jun 2025 MCOP accepted at ICCV 2025.
Jun 2025 Received M.S. from UCAS, CRIPAC / CASIA.
Research Interests
Embodied Intelligence
Agents that perceive, reason, and act in the physical world
World Models
Long-horizon prediction and planning for open environments
VLA Systems
Vision–language–action models for generalizable robot control

Publications

Selected work on embodied agents, perception, and planning.

Education

Nanjing University

Ph.D. · 2026 – Present

University of Chinese Academy of Sciences

M.S. in Artificial Intelligence · 2022 – 2025

Huazhong University of Science and Technology

Bachelor's degree · 2018 – 2022