Yang Bai | Ludwig Maximilians Universität München (LMU)

About Me

I am a third-year Ph.D. student at Mathematical Department of LMU Munich (Ludwig-Maximilians-Universität München) and the Huawei Research Center Munich, 2012 Laboratory, under the supervision of Prof. Dr. Gitta Kutyniok. My research focuses on World Model, Embodied AI, and Multi-Modal Diffusion Models.

Before beginning Ph.D., I earned my Master’s degree in Scientific Computing from the Technical University of Berlin (TUB) and ETH Zurich, where I worked in the Scalable Parallel Computing Laboratory (SPCL) and graduated with high distinction. I received my Bachelor’s degree in Safety Engineering from the University of Science and Technology Beijing (USTB).

Research Interests

Computer Vision: Controllable Video Generation, World Model, Multi-Modal Diffusion Model
Emboddied AI: Robotic Policy learning, Vision-Language-Action model (VLA)

News

[Jun. 2026] ✈ I’ll be attending ICRA 2026 (Wien, Austria) for presentation — feel free to reach out if you’d like to connect and chat!
[May. 2026] ✈ I’ll be attending ICASSP 2026 (Barcelona, Spain) for presentation — feel free to reach out if you’d like to connect and chat!
[Mar. 2026] 🎉 One of our paper on Soft Robotics Policy using Rectified Flow is accepted to RA-L!
[Jan. 2026] 🎉 Two of our paper on Emboddied AI are accepted to ICRA 2026 main conference!
[Jan. 2026] 🎉 One of my paper on Physics Signal Enhanced (Multi-Modal) Video generation is accepted to ICASSP 2026 main conference!
[Oct. 2025] ✈ I’ll be attending IROS 2025 (Hangzhou, China) for an oral presentation — feel free to reach out if you’d like to connect and chat!
[Juli. 2025] 🎉 Two of our paper on Emboddied AI video generation are accepted to IROS 2025 main conference!
[Feb. 2024] 🎖 I go for Huawei Pangu Video Generation Model development in person!
[Oct. 2023] 📍 I start my PhD journey!

Publications

RA-L

Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping

Liudi Yang*, Yang Bai*, Yuhao Wang*, Ibrahim Alsarraj, Gitta Kutyniok, Zhanchi Wang, Ke Wu(*Equal contribution.)

IEEE Robotics and Automation Letters (RA-L)

PDF BibTex

ICRA 2026

CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion

Liudi Yang, Yang Bai, George Eskandar, Fengyi Shen, Mohammad Altillawi, Dong Chen, Ziyuan Liu, Abhinav Valada

The IEEE International Conference on Robotics and Automation (ICRA), 2026.

PDF BibTex

ICRA 2026

DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos

Yang Bai, Liudi Yang, George Eskandar, Fengyi Shen, Mohammad Altillawi, Ziyuan Liu, Gitta Kutyniok

The IEEE International Conference on Robotics and Automation (ICRA), 2026.

PDF Project Page BibTex

ICASSP 2026

Physics-Informed Video Diffusion For Shallow Water Equations

Yang Bai, George Eskandar, Ziyuan Liu, Gitta Kutyniok

The IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026.

PDF BibTex

IROS 2025

RoboSwap: A GAN-driven Video Diffusion Framework For Unsupervised Robot Arm Swapping

Yang Bai, Liudi Yang, George Eskandar, Fengyi Shen, Dong Chen, Mohammad Altillawi, Ziyuan Liu, Gitta Kutyniok,

The IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS), 2025.

PDF Project Page BibTex Oral Presentation

IROS 2025

RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation

Liudi Yang*, Yang Bai*, George Eskandar, Fengyi Shen, Mohammad Altillawi, Dong Chen, Soumajit Majumder, Ziyuan Liu, Gitta Kutyniok, Abhinav Valada(*Equal contribution.)

The IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS), 2025.

PDF Project Page BibTex Oral Presentation

Services

Conference Reviewers

Organizational Experience

Chair for the Deep Learning Method Session on IROS 2025