Zum Inhalt springen
Technische Universität München

Yuan Meng

Picture of Yuan Meng

Yuan Meng

Technical University of Munich

Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems (Prof. Knoll)

  • E-mail: y.meng@tum.de

Curriculum Vitae

Yuan Meng now works as a Ph.D. candidate at the Technical University of Munich (TUM) since 2024, where he focuses on 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 dynamic environments.

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.

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

Available Thesis Topics

I am always excited to collaborate with highly self-motivated and outstanding students. Research topics in my group are released on an continual basis and may not always be listed on the official proposal page. If you are interested in embodied intelligence and robotic manipulation tasks, please feel free to reach out to me at any time. I expect prospective students to meet the following criteria before starting a thesis or research project:

  • Proficiency in Python, Linux OS and a solid understanding of deep learning.
  • Good English communication and academic writing skills.
  • Good academic performance (GPA < 2.3).
  • Availability for full-time work at least 6 months.
  • Prior experience with reinforcement learning/ imitation learning is highly desirable and will be considered an advantage.

Outstanding candidates may have the opportunity to co-author papers with our group for top-tier journals and conferences.

When applying for a research project, please include the following materials in your email:

  • Your CV (including relevant coursework, projects, and skills)
  • Academic transcript
  • A brief summary highlighting your background and motivation
  • The research direction(s) you are most interested in

I will get back to selected candidates within one week.

Currently ongoing research topics (update 2026.03):

  1. Cross-embodiment lifelong reinforcement learning
  2. World action model for humanoid manipulation with action space disentanglement
  3. LLM-based code generation for humanoid manipulation

Thesis Supervision

Master Thesis: 

Research TopicsDurationName
On-policy Multitask Reinforcement Learning on Quadruped Locomotion2025.01 - 2025.07Xintong He
Multitask Reinforcement Learning using MoE on Quadruped Robots2025.09 - 2026.02Pavel Kharitenko
Cross-embodiment lifelong learning with shared knowledge representation2026.03 - ongoingGaojian Xie
Humanoid vision language action model for parcel sorting loco-manipulation2026.03 - ongoingBo Wang
Humanoid vision language action model with failure recovery adaptation2026.04 - ongoingYushan Zheng

Guided Research (part time):

Research TopicsDurationName

Inference Knowledge Reuse in Meta-Reinforcement Learning 

(Submit to IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI)

Recommended for a research internship at Leju Robotics & Nanjing University, Suzhou (2026.3 - 2026.9)

2025.05 - 2026.06Bo Wang
World action model with 3D point cloud for spatial semantic enhancement2026.03 - ongoingChang Zhang

 

Academic Service

  • Reviewer, IEEE/ASME Transactions on Mechatronics
  • Reviewer, the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
  • Reviewer, the 2026 International Conference on Machine Learning (ICML 2026)
  • Reviewer, the 2026 International Conference on Learning Representations (ICLR 2026)
  • Reviewer, the 2026 IEEE International Conference on Robotics & Automation (ICRA 2026)
  • Reviewer, the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
  • Reviewer, the 2025 International Conference on Computer Vision (ICCV 2025)

Recent Featured Publications

Our work titled “Preserving and combining knowledge in robotic lifelong reinforcement learning” has been published on Nature Machine Intelligence (2025). (https://www.nature.com/articles/s42256-025-00983-2).

Publications

2026

  • Hu, Ziou; Yao, Xiangtong; Meng, Yuan; Bing, Zhenshan; Knoll, Alois: Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness. , 2026 mehr…
  • Li, Xukun; Sun, Yu; Zhang, Lei; Huang, Bosheng; Peng, Yibo; Meng, Yuan; Jiang, Haojun; Xie, Shaoxuan; Yao, Guacai; Knoll, Alois; others: DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter. arXiv preprint arXiv:2602.05513, 2026 mehr…

2025

  • Meng, Yuan; Bing, Zhenshan; Yao, Xiangtong; Chen, Kejia; Huang, Kai; Gao, Yang; Sun, Fuchun; Knoll, Alois: Preserving and combining knowledge in robotic lifelong reinforcement learning. Nature Machine Intelligence, 2025 mehr…
  • Meng, Yuan; Bing, Zhenshan; Yao, Xiangtong; Chen, Kejia; Huang, Kai; Gao, Yang; Sun, Fuchun; Knoll, Alois: Preserving and combining knowledge in robotic lifelong reinforcement learning. Nature Machine Intelligence 7 (2), 2025, 256-269 mehr…
  • Meng, Yuan; Sun, Zhenguo; Fest, Max; Li, Xukun; Bing, Zhenshan; Knoll, Alois: Growing with your embodied agent: A human-in-the-loop lifelong code generation framework for long-horizon manipulation skills. arXiv preprint arXiv:2509.18597, 2025 mehr…
  • Meng, Yuan; Yao, Xiangtong; Chen, Kejia; Wu, Yansong; Zhang, Liding; Bing, Zhenshan; Knoll, Alois: Pretrained Bayesian non-parametric knowledge prior in robotic long-horizon reinforcement learning. arXiv preprint arXiv:2503.21975, 2025 mehr…
  • Meng, Yuan; Yao, Xiangtong; Ye, Haihui; Zhou, Yirui; Zhang, Shengqiang; Bing, Zhenshan; Knoll, Alois: Data-agnostic robotic long-horizon manipulation with vision-language-guided closed-loop feedback. arXiv preprint arXiv:2503.21969, 2025 mehr…
  • Meng, Yuan; Yao, Xiangtong; Ye, Haihui; Zhou, Yirui; Zhang, Shengqiang; Sun, Zhenguo; Li, Xukun; Bing, Zhenshan; Knoll, Alois: Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation. arXiv preprint arXiv:2503.21969, 2025 mehr…
  • Sun, Zhenguo; Peng, Yibo; Meng, Yuan; Li, Xukun; Huang, Bo-Sheng; Bing, Zhenshan; Wang, Xinlong; Knoll, Alois: RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking. arXiv preprint arXiv:2509.20717, 2025 mehr…
  • Yao, Xiangtong; Blei, Tobias; Meng, Yuan; Zhang, Yu; Zhou, Hongkuan; Bing, Zhenshan; Huang, Kai; Sun, Fuchun; Knoll, Alois: Long-Horizon Language-Conditioned Imitation Learning for Robotic Manipulation. IEEE/ASME Transactions on Mechatronics, 2025, 1-12 mehr…
  • Yao, Xiangtong; Blei, Tobias; Meng, Yuan; Zhang, Yu; Zhou, Hongkuan; Bing, Zhenshan; Huang, Kai; Sun, Fuchun; Knoll, Alois: Long-Horizon Language-Conditioned Imitation Learning for Robotic Manipulation. IEEE/ASME Transactions on Mechatronics, 2025, 1-12 mehr…
  • Yao, Xiangtong; Zhou, Yirui; Meng, Yuan; Dong, Liangyu; Hong, Lin; Zhang, Zitao; Bing, Zhenshan; Huang, Kai; Sun, Fuchun; Knoll, Alois: Pick-and-place manipulation across grippers without retraining: A learning-optimization diffusion policy approach. arXiv preprint arXiv:2502.15613, 2025 mehr…
  • Yao, Xiangtong; Zhou, Yirui; Meng, Yuan; Liu, Yanwen; Dong, Liangyu; Zhang, Zitao; Bing, Zhenshan; Huang, Kai; Sun, Fuchun; Knoll, Alois: Inference-stage Adaptation-projection Strategy Adapts Diffusion Policy to Cross-manipulators Scenarios. arXiv preprint arXiv:2509.11621, 2025 mehr…
  • Zhang, Liding; Wei, Yankun; Cai, Kuanqi; Bing, Zhenshan; Meng, Yuan; Wu, Fan; Haddadin, Sami; Knoll, Alois: CIT*: Context-Based Biased Batch-Sampling for Almost-Surely Asymptotically Optimal Motion Planning. 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2025, 4421-4428 mehr…
  • Zhang, Liding; Wei, Yankun; Cai, Kuanqi; Bing, Zhenshan; Meng, Yuan; Wu, Fan; Haddadin, Sami; Knoll, Alois: CIT: Context-Based Biased Batch-Sampling for Almost-Surely Asymptotically Optimal Motion Planning. 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2025, 4421-4428 mehr…

2023

  • Bing, Zhenshan; Meng, Yuan; Yun, Yuqi; Su, Hang; Su, Xiaojie; Huang, Kai; Knoll, A: Diva: A dirichlet process based incremental deep clustering algorithm via variational auto-encoder. arXiv preprint arXiv:2305.14067, 2023 mehr…
  • Bing, Zhenshan; Meng, Yuan; Yun, Yuqi; Su, Hang; Su, Xiaojie; Huang, Kai; Knoll, Alois: DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder. , 2023 mehr…
  • Chen, Kejia; Bing, Zhenshan; Wu, Fan; Meng, Yuan; Kraft, André; Haddadin, Sami; Knoll, Alois: Contact-Aware Shaping and Maintenance of Deformable Linear Objects With Fixtures. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2023 mehr…
  • Chen, Kejia; Bing, Zhenshan; Wu, Fan; Meng, Yuan; Kraft, André; Haddadin, Sami; Knoll, Alois: Contact-Aware Shaping and Maintenance of Deformable Linear Objects With Fixtures. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 mehr…
  • Yao, Xiangtong; Zhou, Hongkuan; Mees, Oier; Meng, Yuan; Xiao, Ted; Bisk, Yonatan; Oh, Jean; Johns, Edward; Shridhar, Mohit; Shah, Dhruv; Thomason, Jesse; Huang, Kai; Chai, Joyce; Bing, Zhenshan; Knoll, Alois: Bridging language and action: A survey of language-conditioned robot manipulation. , 2023 mehr…
  • Zhou, Hongkuan; Yao, Xiangtong; Meng, Yuan; Sun, Siming; Bing, Zhenshan; Huang, Kai; Knoll, Alois: Language-conditioned Learning for Robotic Manipulation: A Survey. , 2023 mehr…
To top