Xufeng Zhao
with a focus on developing advanced AI for both digital and embodied agent autonomy
Ph.D. student in University of Hamburg
My interests are in a "research triangle": 
- Large language models have high capacities to reason universally
- Reinforcement learning optimize agent behavior to maximize expectations
- Robots embody the intellegence to our real world
news
| Dec 22, 2024 | [#Publications] / Our work Mental Modeling of Reinforcement Learning Agents by Language Models, which studies how/to what degree an LLM can mental model a pre-trained reinforcement learning agent, has been accepted at journal TMLR. |
|---|---|
| Sep 25, 2024 | Activity / ICRA@40 - Happy Birthday ICRA! |
| Sep 10, 2024 | [#Publications] / Our work Large Language Models for Orchestrating Bimanual Robots, which studies how bimanual robots (see more about our NICOL robot) can benefit from LLMs for efficient two-hand collaboration, has been accepted at Humanoids 2024, scheduled on November 22-24, Nancy, France. |
| Jun 16, 2024 | [#Publications] / Our work Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning, which studies how object status influences robotic decision/manipulation, has been accepted at ICANN 2024, scheduled for September 17 to September 20, 2024, in Switzerland. |