World Model
Learning predictive representations of environment dynamics for reasoning, planning, and decision-making.

Research directions
My work connects world modeling, robot learning, and video generation. I am especially interested in representations that capture how environments evolve and support reliable physical interaction.
View all publicationsLearning predictive representations of environment dynamics for reasoning, planning, and decision-making.
Developing learning systems that turn interaction and feedback into robust, transferable robot skills.
Building controllable video models that capture temporal dynamics and generate coherent future visual states.
Experience
Dexterous-hand manipulation with VLA models and exploratory work on World Action Models.
Research on real-hardware interaction, robot learning, and world modeling at LEAP Lab.
Embodied AI and generative-model research with Prof. Kwang In Kim.
Harbin Institute of Technology
Research foundations in embodied intelligence, generative AI, and temporal reasoning.