Taeyoung Yeon

prof_pic.jpg

About Me

I am a PhD student at NYU Tandon in the Human-Centered Technology Innovation and Design program, advised by Professor Vedant Das Swain. Previously, I served as a Post-Baccalaureate Research Fellow at Northwestern University, advised by Professor Karan Ahuja. I earned a Bachelor of Science in Computer Science and Engineering from Seoul National University. Additionally, I worked at the mobile game company, Awesomepiece, as a Full Stack Game Developer.

My research targets practical human sensing: sensing a person’s context with consumer devices for real-time interactions, using only built-in sensors such as IMUs and microphones. I use this sensing to add human context for a natural flow of interaction with AI agents.

đź“„ You can view and download my full CV here.

news

Oct 12, 2026 Our ISMAR 2026 paper, FlowAvatar, is now on arXiv, and the code is public.
Sep 15, 2026 Submitted a paper to ICRA 2027.
Aug 23, 2026 Starting my PhD at NYU Tandon School of Engineering, advised by Prof. Vedant Das Swain. :sparkles:
Aug 01, 2026 My co-first-author paper (FlowAvatar: Real-Time Full-Body Avatars from Sparse Egocentric Inputs on Consumer XR Devices) was accepted to ISMAR 2026! Check my homepage for details.
Feb 09, 2026 Our paper has been accepted to CVPR 2026 Findings!

publications

  1. flowavatar_teaser.png
    FlowAvatar: Real-Time Full-Body Avatars from Sparse Egocentric Inputs on Consumer XR Devices
    Chenfeng Gao*, Taeyoung Yeon*, Sungheon Park, and 4 more authors
    In Proceedings of the 2026 IEEE International Symposium on Mixed and Augmented Reality (ISMAR ’26), 2026
  2. teaser_MARIO.png
    MARIO: Motion-Augmented Real-Time Multi-Sensor Inertial Odometry
    Yiquan Li*, Taeyoung Yeon*, Chenfeng Gao, and 3 more authors
    In Proceedings of the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Findings), 2026
  3. Process.png
    WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
    Taeyoung Yeon, Vasco Xu, Henry Hoffmann, and 1 more author
    In Proceedings of the 27th ACM International Conference on Multimodal Interaction, 2025