Yunfu Deng

I am a robotics PhD candidate at the University of Wisconsin–Madison, advised by Prof. Josiah P. Hanna. My research investigates how robots can learn predictive models of real-world dynamics from limited interaction data, with an emphasis on representations that generalize beyond the data they were trained on. I am currently extending this toward world models that support long-horizon planning and decision-making for manipulation and embodied agents.

I believe capable, general-purpose robots will come from a real understanding of physical-world dynamics—not from scaling models that have never touched the world. I am trying to turn Gundam (EX-S / ALICE) into reality.