Yanming Xiu (修彦名)

Greetings! I am currently a 3rd year Ph.D. candidate at Intelligent Interactive Internet of Things (I^3T) Lab , Department of Electrical and Computer Engineering, Duke University in Durham, NC, where I work on computer vision, deep learning and medical imaging. My Advisor is Dr. Maria Gorlatova.

Prior to coming to Duke, I earned my B.Eng. in Automation and a honor undergraduate degree at Zhejiang University in 2022. I also worked as a research assistant at the University of Hong Kong in 2021.

CV  /  Email  /  Github  /  Linkedin  /  Google Scholar

Research Interests

I'm interested in machine learning and its application in computer vision, especially Augmented Reality (AR) and Virtual Reality (VR). Currently I am also interested in generative AI and its application.

Experiences

• Dec. 2023 - Now: Research Assistant, Department of Electrical and Computer Engineering, Duke University

  Advisor: Dr. Maria Gorlatova



• Aug. 2022 - Nov. 2023: Research Assistant, Department of Psychiatry and Behavioral Science, Duke University

  Advisor: Dr. Yun Wang, Prof. Jonathan Posner



• Jul. 2021 - Dec. 2021: Research Assistant, Department of Computer Science, University of Hong Kong

  Advisor: Prof. Wenping Wang



• Mar. 2020 - May. 2021: Research Assistant, College of Control Science and Engineering, Zhejiang University

  Advisor: Prof. Jiming Chen

Education

• Aug. 2022 - Now: Ph.D. Student, Department of Electrical and Computer Engineering, Duke University

  GPA: 3.86/4.00



• Aug. 2018 - Jun. 2022: B.Eng in Automation, College of Control Science and Engineering, Zhejiang University

  GPA: 3.85/4.00



• Aug. 2018 - Jun. 2022: Honors Degree, Chu-Kochen Honors College, Zhejiang University

Honors

• Jun. 2022: Outstanding Undergraduate Graduates, Zhejiang University (Top 10%)


• Oct. 2021: First Tier Scholaship for Academic Excellence, Zhejiang University (Top 5%)

Publications (*Equal Contributions)

• ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality
  Yanming Xiu, Tim Scargill, Maria Gorlatova.
  IEEE Transactions on Visualization and Computer Graphics (TVCG), 2025
  Paper / Video / Github Repo


• Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble
  Lin Duan*, Yanming Xiu*, Maria Gorlatova.
  IEEE VR 2025: Generative AI meets eXtended Reality (GenAI-XR) Workshop, 2025
  Paper / Github Repo


• Vision Language Model-Based Solution for Obstruction Attack in AR: A Meta Quest 3 Implementation
  Yanming Xiu, Maria Gorlatova.
  IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2025
  Paper / Video


• LOBSTAR: Language model-based obstruction detection for augmented reality
  Yanming Xiu, Tim Scargill, Maria Gorlatova.
  IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2024
  Paper / Poster

Other Projects

Some of my previous projects are listed here:

This is a joint project co-advised by Prof. Wenping Wang from HKU and Prof. Yiping Feng from ZJU. The project include 3 parts: 1) clothes landmark detection through HRNet, 2) Robotic arm path planning and 3) Overall system construction. The camera takes an image of clothes and pass it to my fork version of HRNet . Then the HRNet predict the key points of the clothes and pass them to robot control script. Finally, the arm execute the folding process.

This is a competition held by ZJU CSE. The participants are required to control the robot arm and hit the bells for as much times as possible within 1 minute, while obstacle avoidance is also required. I loaded the robot model in Gazebo, implemented the torque control algorithm and tested it in real-world robot.

This is a training program in 2020, in which I designed a new type of chipless RFID tag so that the production cost of tags can be reduced. The tag can be correctly detected by the RFID reader at around 5-80 cm, which are common detection distances for warehouse logistics tasks.