Curriculum vitae

Yuan Meng is a Ph.D. candidate at the Technical University of Munich (TUM) from 2024, where he focuses on Multimodal Large Language Model (MLLM) empowered embodied AI and lifelong robotic intelligence. His research explores innovative ways to integrate artificial intelligence into physical robotic systems, aiming to create adaptive, intelligent robots that can operate seamlessly in complex and unstructured environments.

Prior to his Ph.D. studies, Mr. Meng earned his Master’s degree in Mechatronics and Robotics from TUM in 2023. During this time, he specialized in robotic reinforcement learning, optimal control, and embodied AI, gaining deep insights into intelligent automation systems.

Mr. Meng received his Bachelor’s degree in Mechanical Engineering from RWTH Aachen University in 2020.

Available thesis topics

I am always looking forward to working with highly motivated and exceptional students. Research topics under my supervision are released continually and may not always be listed on the official proposal page. Therefore, if you are self-motivated for a robotic and/or embodied AI related thesis topic, please write me an email indicating your background and skills. I expect prospective students to meet the following criteria before starting their thesis or project:

• A strong interest in embodied AI, with a proactive and problem-solving mindset.
• Good command of academic English, particularly in reading and writing.
• Solid programming skills in Python.
• Good academic performance (grade ≤ 2.3).
• Availability for at least 6 months of full-time commitment.

Outstanding candidates will have the opportunity to co-author publications with our team in top-tier conferences and journals.

When applying, please include the following in your email, I will get back to suitable candidates within one week:

• A CV detailing relevant coursework, projects, and technical skills
• Your academic transcript
• A short introduction highlighting your background and interests, tailored to your experience
• Your preferred research direction(s)

Currently available ongoing thesis directions:

1. Cross-embodiment lifelong reinforcement learning
2. Embodied meta-reinforcement learning
3. Large language model empowered robotic manipulation

Recent featured publications

Our recent work titled “Preserving and combining knowledge in robotic lifelong reinforcement learning” has been published on Nature Machine Intelligence (https://www.nature.com/articles/s42256-025-00983-2).