Duke University · Electrical & Computer Engineering

Yanming Xiu 修彦名

I am a Ph.D. candidate in the Intelligent Interactive Internet of Things (I³T) Lab at Duke University, advised by Prof. Maria Gorlatova.

My research focuses on safe and trustworthy augmented reality, scene understanding, and vision-language models. I develop systems and benchmarks for detecting task-detrimental and deceptive virtual content, and for assessing and improving AR content quality.

Selected News

Jun 2026Our paper “Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality” has been accepted to the CVPR 2026 Findings Track.
Oct 2025Our paper “Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach” received the Best Paper Award at IEEE ISMAR 2025 (Top 1%).
Oct 2025I received the Best Doctoral Consortium Presentation Award at IEEE ISMAR 2025 for “Toward Safe, Trustworthy and Realistic Augmented Reality User Experience.”
Oct 2025Our paper “Say It, See It: A Systematic Evaluation on Audio-Based 3D Content Generation Methods in Augmented Reality” received the Best Workshop Paper Award at the IEEE ISMAR 2025 UNAI Workshop.
Jul 2025Our paper “Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach” has been accepted to IEEE Transactions on Visualization and Computer Graphics (TVCG) and presented at IEEE ISMAR 2025.
Jan 2025Our paper “ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality” has been accepted to IEEE Transactions on Visualization and Computer Graphics (TVCG) and presented at IEEE VR 2025.

Publications

* equal contribution · † student mentee

2026

CVPR Findings 2026

Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

Yanming Xiu, Zhengyuan Jiang, Neil Zhenqiang Gong, Maria Gorlatova

Paper

CVPR Findings 2026

Cognitive Attacks Detection in Augmented Reality (CADAR): A Neuro-Symbolic Approach with Particle Filtering on Perception Graphs

Rongqian Chen, Allison Andreyev, Yanming Xiu, Joshua Chilukuri†, Shunav Sen†, Mahdi Imani, Bin Li, Maria Gorlatova, Gary Tan, Tian Lan

Paper

SOUPS 2026

Is It Real? Exploiting Virtual-Physical Discrimination Vulnerability in Mixed Reality

Xueyang Wang, Xihuan Yao, Yanming Xiu, Xin Yi, Maria Gorlatova, Hewu Li

arXiv

IEEE VR Workshop 2026

User Prompting Strategies and Prompt Enhancement Methods for Open-Set Object Detection in XR Environments

Junfeng Lin†, Yanming Xiu, Maria Gorlatova

Paper

2025

IEEE TVCG / ISMAR 2025 · Best Paper Award

Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach

Yanming Xiu, Maria Gorlatova

Paper GitHub

IEEE Internet Computing 2025

Probing the Augmented Reality Scene Analysis Capabilities of Large Multimodal Models: Toward Reliable Real-Time Assessment Solutions

Lin Duan, Elias Rotondo, Yanming Xiu, Sangjun Eom, Ryan Chen, Conrad Li, Yuhe Hu, Maria Gorlatova

Paper

IEEE TVCG / IEEE VR 2025

ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality

Yanming Xiu, Tim Scargill, Maria Gorlatova

Paper Video GitHub

IJCNLP-AACL Findings 2025

Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?

Sazia Tabasum Mim, Jack Morris, Manish Dhakal, Yanming Xiu, Maria Gorlatova, Yi Ding

Paper arXiv

ISMAR Adjunct 2025 · Best Workshop Paper Award

Say It, See It: A Systematic Evaluation on Audio-Based 3D Content Generation Methods in Augmented Reality

Yanming Xiu, Joshua Chilukuri†, Shunav Sen†, Maria Gorlatova

Paper

IEEE VR Workshop 2025

Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble

Lin Duan*, Yanming Xiu*, Maria Gorlatova

Paper GitHub

ISMAR Doctoral Consortium 2025 · Best Presentation Award

Toward Safe, Trustworthy and Realistic Augmented Reality User Experience

Yanming Xiu, Maria Gorlatova

Paper

IEEE VR Research Demonstration 2025

Vision Language Model-Based Solution for Obstruction Attack in AR: A Meta Quest 3 Implementation

Yanming Xiu, Maria Gorlatova

Paper Video

ACM MobiHoc Workshop Demonstration 2025

Demonstrating Visual Information Manipulation Attacks in Augmented Reality: A Hands-On Miniature City-Based Setup

Yanming Xiu, Maria Gorlatova

Paper

2024

ISMAR Adjunct 2024

LOBSTAR: Language Model-Based Obstruction Detection for Augmented Reality

Yanming Xiu, Tim Scargill, Maria Gorlatova

Paper Poster

Education

Duke University

Ph.D. Student, Electrical and Computer Engineering

Aug 2022 – Present

Zhejiang University

B.Eng. in Automation and Robotics, Chu Kochen Honor Class

Sep 2018 – Jun 2022

Teaching & Mentoring

Teaching Assistant, ECE 687D

Theory and Algorithms of Machine Learning

Fall 2025

Teaching Assistant, ECE 356

Computer Networks

Fall 2024

High School Research Mentor

Mentored four NCSSM students across two research projects.

Jun 2024 – Present

Selected Honors

Oct 2025Best Paper Award, IEEE ISMAR
Oct 2025Best Doctoral Consortium Presentation Award, IEEE ISMAR
Oct 2025Best Workshop Paper Award, IEEE ISMAR UNAI Workshop
Sep 2025Graduate Program Research Workshop Student Talk Session Runner-Up, Duke ECE
Jun 2022Outstanding Graduate, Chu Kochen Honors College, Zhejiang University

Professional Service

Journal reviewer: Pattern Recognition, IEEE Network, International Journal of Human-Computer Interaction, Neurocomputing, and Engineering Applications of Artificial Intelligence.

Conference reviewer: ACM VRST and EuroXR; external reviewer for CVPR, MobiSys, SenSys, SIGCOMM, and MobiCom.