Yuheng Wu 吴宇恒

#Publications

Conference and Journal Papers

2026

1. 

   NavSight in the Wild: Understanding Real-World Use of a Mobile Augmented Reality Application for People with Low Vision in Outdoor Navigation

   Yuheng Wu, Kexin Zhang, Ben Kosa, Ru Wang, Sanbrita Mondal, and Yuhang Zhao

   IMWUT, 2026

   📱 Available on Apple App Store soon

   PDF Abstract

   The ability to navigate outdoors safely and independently is crucial yet challenging for people with low vision (PLV). While various augmented reality (AR) systems for low vision have been designed and evaluated in ideal lab environments, no research has investigated their real-world feasibility and challenges. We present NavSight, a mobile AR application that assists PLV in outdoor navigation by recognizing important outdoor objects (e.g., curb, vehicle) and rendering real-time visual augmentations. Through a seven-day diary study with 12 PLV in real-world settings, we characterize the impact of NavSight on scene perception, users' configuration strategies on what objects to augment and how to augment them across scenarios, how users made sense of and responded to recognition errors, and the social acceptability of using NavSight in public. We further identify environmental factors affecting recognition, such as weather conditions, lighting and shadows, and nonstandard road markings and textures, as well as usability issues in daily use. We discuss these real-world challenges and derive design implications for future AI-powered assistive AR systems for outdoor use.

2. 

   What to Distinguish and How? Opportunities and Challenges of Augmenting Multiple, Cluttered Objects in Complex Scenes for People with Low Vision

   Yuheng Wu, Ruijia Chen, Jaewook Lee, Jia Li, Kexin Zhang, Meng Fong Lio, and 5 more authors

   ASSETS, 2026

   PDF Abstract Code Cite

   People with low vision (PLV) struggle to perceive complex scenes like busy kitchens and crowded streets, which contain many objects, visual clutter, and dynamic elements. Prior AR systems for low vision either enhance low-level visual features or augment task-relevant objects for single tasks in simple settings, leaving multi-object augmentation in complex scenes underexplored. Informed by a formative study characterizing important objects and their perceived importance for PLV, we built SceneGlance, a wearable AR system that recognizes important objects and visually distinguishes them by importance level. Through a controlled lab study with 12 PLV in a mock-up kitchen scene and a free-form think-aloud study with 13 PLV navigating an outdoor route, we found that AR distinction on object importance shifted PLV's attention toward objects of higher importance, and supported perception strategies such as building mental snapshots from the augmentation distribution and hierarchical scanning by importance. However, this attention shift came with a tradeoff of reduced overall scene recall. The studies also surfaced challenges posed by AR augmentations in complex scenes, such as adjacent augmentations blending or interfering with each other, yielding design implications for more practical AR vision enhancement systems in the complex real world.

   @inproceedings{wu2026distinguish,
     title = {What to Distinguish and How? Opportunities and Challenges of Augmenting Multiple, Cluttered Objects in Complex Scenes for People with Low Vision},
     author = {Wu, Yuheng and Chen, Ruijia and Lee, Jaewook and Li, Jia and Zhang, Kexin and Lio, Meng Fong and Wang, Weibing and Mondal, Sanbrita and Froehlich, Jon E. and Tian, Yapeng and Zhao, Yuhang},
     booktitle = {ASSETS},
     year = {2026},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     series = {ASSETS '26},
     isbn = {979-8-4007-2521-0},
     doi = {10.1145/3797867.3828974},
     url = {https://doi.org/10.1145/3797867.3828974},
   }

3. 

   NaviNote: Enabling In-situ Spatial Annotation Authoring to Support Exploration and Navigation for Blind and Low Vision People

   🏆 Honorable Mention | 📜 US Patent Pending

   Ruijia Chen^*, Yuheng Wu^*, Charlie Houseago, Filipe Gaspar, Filippo Aleotti, Dorian Gálvez-López, and 6 more authors

   * Equal contribution

   CHI, 2026

   PDF Abstract Cite Video

   GPS and smartphones enable users to place location-based annotations, capturing rich environmental context. Previous research demonstrates that blind and low vision (BLV) people can use annotations to explore unfamiliar areas. However, current commercial systems allowing BLV users to create annotations have never been evaluated, and current GPS-based systems can deviate several meters. Motivated by high-accuracy visual positioning technology, we first conducted a formative study with 24 BLV participants to envision a more accurate and inclusive annotation system. Surprisingly, many participants viewed the high-accuracy technology not just as an annotation system but also as a tool for precise last-few-meters navigation. Guided by participant feedback, we developed NaviNote, which combines vision-based high-precision localization with an agentic architecture to enable voice-based annotation authoring and navigation. Evaluating NaviNote with 18 BLV participants showed that it significantly improved navigation performance and supported users in understanding and annotating their surroundings. Based on these findings, we discuss design considerations for future accessible annotation authoring systems.

   @inproceedings{chen2026navinote,
     title = {NaviNote: Enabling In-situ Spatial Annotation Authoring to Support Exploration and Navigation for Blind and Low Vision People},
     author = {Chen, Ruijia and Wu, Yuheng and Houseago, Charlie and Gaspar, Filipe and Aleotti, Filippo and Gálvez-López, Dorian and Johnston, Oliver and Mazala, Diego and Garcia-Hernando, Guillermo and Bandukda, Maryam and Brostow, Gabriel and Van Brummelen, Jessica},
     booktitle = {CHI},
     year = {2026},
     isbn = {9798400722783},
     doi = {10.1145/3772318.3790589},
     url = {https://doi.org/10.1145/3772318.3790589},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     articleno = {948},
     numpages = {22},
     series = {CHI '26},
   }

4. 

   AskNow: An LLM-powered Interactive System for Real-Time Question Answering in Large-Scale Classrooms

   Ziqi Liu, Yuankun Wang, Hui-Ru Ho, Yuheng Wu, Yuhang Zhao, and Bilge Mutlu

   CHI, 2026

   PDF Abstract Cite

   In large-scale classrooms, students often struggle to ask questions due to limited instructor attention and social pressure. Based on findings from a formative study with 24 students and 12 instructors, we designed AskNow, an LLM-powered system that enables students to ask questions and receive real-time, context-aware responses grounded in the ongoing lecture and that allows instructors to view students' questions collectively. We deployed AskNow in three university computer science courses for a week and tested with 117 students. To evaluate AskNow's responses, each instructor rated the perceived correctness and satisfaction of 100 randomly sampled AskNow-generated responses. In addition, we conducted interviews with 24 students and the three instructors to understand their experience with AskNow. We found that AskNow significantly reduced students' perceived time to resolve confusion. Instructors rated AskNow's responses as highly accurate and satisfactory. Instructor and student feedback provided insights into the role of such systems in supporting real-time learning in large lecture settings.

   @inproceedings{liu2026asknow,
     title = {AskNow: An LLM-powered Interactive System for Real-Time Question Answering in Large-Scale Classrooms},
     author = {Liu, Ziqi and Wang, Yuankun and Ho, Hui-Ru and Wu, Yuheng and Zhao, Yuhang and Mutlu, Bilge},
     booktitle = {CHI},
     year = {2026},
     isbn = {9798400722783},
     doi = {10.1145/3772318.3790328},
     url = {https://doi.org/10.1145/3772318.3790328},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     articleno = {944},
     numpages = {22},
     series = {CHI '26},
   }

2022

1. 

   TreeVisual: Design and Evaluation of a Web-Based Visualization Tool for Teaching and Learning Tree Visualization

   Brendan J. O'Handley, Yuheng Wu, Haobin Duan, and Chaoli Wang

   ASEE Annual Conference & Exposition, 2022

   PDF Abstract Demo Code Cite

   Trees are a common form of visual representation that encode hierarchical data structures in parent-children relationships. Although many software tools can visualize tree structures, there is a lack of tools designed for teaching and learning tree visualization. This paper presents TreeVisual, an educational software tool that visualizes hierarchical data structures with real-world datasets and allows users to explore and manipulate the various forms of tree visualizations via a web interface. We collect four hierarchical datasets from different domains, including academic publication, government structures, global trading statistics, and tree taxonomy. Leveraging D3.js, TreeVisual supports four popular hierarchical layouts and their variants: pack, radial tree and its collapsible version, sunburst, and treemap and its zoomable version. Furthermore, TreeVisual allows users to comprehend, compare, and critique these layouts in side-by-side display panels, supported by a set of interactive functions. These functions include appearance changes, filtering of intermediate nodes, and selection of leaf nodes. Users can utilize these functions to filter the tree hierarchies, pinpoint nodes of interest, drill down to varying levels of detail, and glean data-related insights. To demonstrate the usefulness of TreeVisual and assess its effectiveness, we conducted a formal user study with students enrolled in a college-level Data Visualization course. The study involves an introduction to the tool, a training session, an in-class quiz integrated into TreeVisual, and a survey. The instructor introduced TreeVisual after related tree visualization concepts and algorithms were covered, followed by an exploration of the tool by the students. Students then performed a pre-quiz with five questions to get familiar with the types of questions that would appear in the actual quiz. A week later, students took the actual quiz of 22 questions in class, followed by a survey that asks for their feedback on tree layouts, datasets, user interface, and general impression of TreeVisual.

   @inproceedings{ohandley2022treevisual,
     title = {TreeVisual: Design and Evaluation of a Web-Based Visualization Tool for Teaching and Learning Tree Visualization},
     author = {O'Handley, Brendan J. and Wu, Yuheng and Duan, Haobin and Wang, Chaoli},
     booktitle = {ASEE Annual Conference & Exposition},
     year = {2022},
   }

Doctoral Symposium

2026

1. 

   Scene-Aware Augmented Reality for People with Low Vision in Complex, Dynamic Environments

   Yuheng Wu

   UIST Adjunct, 2026

Workshop Papers

2026

1. Preliminary Exploration on Intelligent Social Cues in Wearable Augmented Reality to Support Passing Encounters for People with Low Vision

   Ben Kosa, Kexin Zhang, Yuheng Wu, Sanbrita Mondal, and Yuhang Zhao

   Next Steps for Augmented Reality On-the-Move: Challenges & Opportunities, CHI Workshop, 2026