Embodied Intelligence
and Robot Learning.

I had the privilege of presenting my recent work on Robotic World Model (RWM) and Uncertainty-Aware Robotic World Model (RWM-U) at the ARCAD Lab, University of Michigan. In this talk, I discussed how we can leverage model-based methods for real-world online reinforcement learning in robotics, and how uncertainty awareness can be incorporated into the training of robotic world models to enhance policy optimization in imagination.

Together with Julian Eßer, Gabe Margolis, and Huazhe Xu, I had the privilege of organizing the Sim-to-Real Transfer for Humanoid Robots Workshop at the 2025 International Conference on Humanoid Robots in Seoul, South Korea. The workshop brought together leading researchers and practitioners to discuss the latest advances and challenges in bridging the gap between simulation and real-world humanoid control.

In this talk, I had the privilege of presenting a comprehensive overview of my experience in the field of Learning from Demonstrations. I discussed the evolution of LfD techniques from feature-based methods to modern generative approaches such as GAN-based learning, and highlighted how these methods have shaped current trends in both robotics and character animation.

While learning from demonstrations has become a widely adopted strategy, many practitioners choose methods based on precedent or anecdotal success rather than a systematic understanding of the algorithmic factors driving performance. Drawing on our extensive experience in the field, we developed Feature-Based vs. GAN-Based Imitation: When and Why, a comprehensive survey designed to provide structured guidance and serve as a practical resource for the community.

The graduation ceremony officially concludes my master's studies at ETH Zurich. It was an unforgettable reunion of friends who shared this great journey with me. I am grateful for the opportunity to have met so many wonderful people during my studies. I am excited to see where our paths will lead us next.

Our work FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning was accepted to the Generative Models for Decision Making (GenAI4DM) workshop at The Twelfth International Conference on Learning Representations (ICLR). This workshop aims to bring together researchers and practitioners from the fields of generative AI and decision making to explore the latest advances, methodologies, and applications.

Our team won second prize with our Llama-2-70b-chat defense in the Large Language Models Capture-the-Flag (LLM CTF) competition at 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). In this competition, participants assume the roles of defenders who craft prompts and filters to instruct an LLM to keep a secret, aiming to prevent its discovery in a conversation.

I am excited to share that I started my Ph.D. program as a doctoral fellow at ETH AI Center at ETH Zurich, Switzerland. I am honored to be co-supervised by Prof. Andreas Krause and Prof. Marco Hutter.

I am thrilled to wrap up my visit with the talented team at the Biomimetic Robotics Lab at Massachusetts Institute of Technology (MIT), Cambridge, United States. It has been an invaluable experience, collaborating on cutting-edge legged robotics. I am eager to see our collective efforts make a meaningful impact on the robot learning community!

It was wonderful to have met my old and new friends during IEEE International Conference on Robotics and Automation (ICRA) 2023 in London, United Kingdom. I am excited to see that our work Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions has been acknowledged by the greatest roboticists in the field. Thanks to the team Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey and Georg Martius, who made this work possible.

Our work Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions was accepted to the Agile Movements: Animal Behavior, Biomechanics, and Robot Devices workshop at IEEE International Conference on Robotics and Automation (ICRA) 2023. This workshop invites researchers to identify the challenges and opportunities of understanding and improving robotic agility from a diverse range of areas, including biology, biomechanics, mechanism design, and control.

My work on Solo robots during my internship at the Max Planck Institute for Intelligent Systems was covered in NANO on 3sat. In the coverage, Prof. Georg Martius explained how autonomous learning systems can obtain extraordinary intelligence from interactions with the environment.

Starting from January, I am honored to work with Prof. Sangbae Kim at Biomimetic Robotics Lab at Massachusetts Institute of Technology (MIT), Cambridge, United States. My main research topic focuses on developing latent skill representation for the MIT Humanoid robot. I am happy to collaborate with Steve Heim and Elijah Stanger-Jones on this exciting topic.

It was wonderful to have met all the great names and my future collaborators and advisors during Conference on Robot Learning (CoRL) 2022 in Auckland, New Zealand. I am excited to see that our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations has been acknowledged by the greatest roboticists in the field and was named a finalist for the Best Paper Award. Thanks to the team Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger and Georg Martius, who made this achievement possible.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was presented to the scholars at the Machines in Motion Laboratory led by Prof. Ludovic Righetti at New York University. The Machines in Motion Laboratory focuses on understanding the fundamental principles for robot locomotion and manipulation that will endow robots with the robustness and adaptability necessary to efficiently and autonomously act in an unknown and changing environment.

I am glad to share that I will join the Biomimetic Robotics Lab led by Prof. Sangbae Kim at Massachusetts Institute of Technology (MIT) to complete my master thesis later this year. The Biomimetic Robotics Lab focuses on designing and controlling robots using insights taken from the natural world. I will be working with the MIT Humanoid on human demonstration imitation.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was accepted to the Learning for Agile Robotics workshop at Conference on Robot Learning (CoRL) 2022. This workshop invites researchers working on making agile robots. The goals include fostering collaboration, understanding the current limitations and inefficiencies, learning common ideas on modern ML based approaches, etc.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was covered by Video Friday collection at IEEE Spectrum. Video Friday is a weekly selection of state-of-the-art robotics videos, collected by scholars at IEEE Spectrum Robotics. This time, our overview video was selected and well acknowledged.

During the second three months of my internship, I accomplished the work Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions under the guidance of Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey and Prof. Georg Martius. In this work, Solo obtained diverse skills by imitating unlabeled, mixed reference motions.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was presented to the scholars at the Robotic Systems Lab (RSL), ETH Zurich during the research presentation. In this weekly event, internal and external researchers are invited to present their state-of-the-art discoveries in fields including robotic system integration and control methods.

The experiments of our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations were presented to the public at the Tübingen Science & Innovation Days. In this event, research institutes including the Max Planck Institute for Intelligent Systems open their doors to the interested public and present their research.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was covered by Video Friday collection at IEEE Spectrum. Video Friday is a weekly selection of state-of-the-art robotics videos, collected by scholars at IEEE Spectrum Robotics. Among our selected videos, SOLOBACKFLIP gained particular popularity.

Our work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations was presented to the evaluation committee and Ph.D. scholars from the International Max Planck Research School for Intelligent Systems (IMPRS) during the on-site evaluation.

During the first three months of my internship, I accomplished the work Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations under the guidance of Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger and Prof. Georg Martius. In this work, Solo developed highly dynamic skills by imitating rough, partial, human-demonstrated reference motions.

Starting from April, I am honored to work with Prof. Georg Martius at Autonomous Learning Group at Max Planck Institute for Intelligent Systems (MPI-IS), Tübingen, Germany. My main research topic focuses on agile skill development and style diversification for Solo robot. This work is closely collaborated with Robotic Systems Lab (RSL), ETH Zurich, Switzerland.

By employing a novel compositional control structure, ANYmal learned to achieve full-pose trajectory tracking in a global coordinate system. A hierarchical system pipeline was introduced, where the high-level policy processes global target information and outputs low-level composition signals and commands with trivial regularization.

From October, I am honored to work on a semester project on the skill integration for ANYmal with hierarchical reinforcement learning at Robotic Systems Lab (RSL) directed by Prof. Marco Hutter. The main research topic focuses on extending locomotion and manipulation capabilities for legged systems by leveraging appropriate combination of acquired skills. This project is mainly supervised by Yuntao Ma, Takahiro Miki and Mayank Mittal.

After having achieved top grades in the course Linear & Combinatorial Optimization (L&CO, 11 ECTS) instructed by Prof. Rico Zenklusen at ETH Zurich last semester, I was honored to take a teaching assistant position for the new semester. Among my responsibilities, I enjoyed delivering lectures the most.

From July 2 to 9, I was honored to participate in the ETH Robotics Summer School directed by ETH RobotX initiative. During this event, a broad scope of components of autonomous mobile robots including state estimation, trajectory optimization, environment mapping, path planning, and artifact detection were introduced and implemented on a wheeled platform, SuperMegaBot. On the last day, we successfully completed an autonomous rescue challenge at the test site.

After receiving offers from top-class universities including University of California, Los Angeles (UCLA), Johns Hopkins University (JHU), École polytechnique fédérale de Lausanne (EPFL), Imperial College London, etc, I decided to pursue my future endeavors in Robotics, Systems and Control under the guidance of Prof. Marco Hutter at ETH Zurich, Switzerland.

Together with 11 other students from the School of Mechanical Engineering, it was my honor to be granted the highest honor for all undergraduates of all majors from more than ten universities in Shanghai this year.

My work on Analysis, Design and Implementation of a Bio-inspired Passive Tail for Amphibious Robots concluded with a novel development of an appropriate chordwise stiffness distribution along a bio-inspired tail for AgnathaX which maximizes the propulsion generated under a combined movement of both passive heaving and pitching.

I am honored to work as a research assistant on the design of a bio-inspired passive tail for amphibious robots at Biorobotics Laboratory (BioRob) directed by Prof. Auke Ijspeert during the last year of my bachelor's study. This project is mainly supervised by Laura Paez.

The Ministry of Education of China funded the China National Scholarship to award outstanding full-time undergraduates for their excellent academic records. Being among the top 1% of the students of the same year again, I am honored to receive this award a second time.

From July to October, I was honored to be selected for the Mitacs Globalink Research Internship program and to work on Design and 3D Printing of Lightweight Advanced Energy Harvesters Made of Smart Materials under the supervision of Prof. Abdolhamid Akbarzadeh. The research was devoted to reinforcing mechanical properties of 3D printing materials by combining pulverized wood particles with melted polymer through a novel process of extrusion.

I am honored to receive my first international award in Mathematics.

The Ministry of Education of China funded the China National Scholarship to award outstanding full-time undergraduates for their excellent academic records. Being among the top 1% of the students of the same year, I am honored to receive this award.