avatar

Jingyu Lee

Ph.D. Candidate

Human-Centered Computer Systems Lab, Seoul National University

jingyu.lee (at) hcs.snu.ac.kr

I am an experimental computer systems researcher at the Human-Centered Computer Systems Lab. I envision future applications unconstrained by existing technologies, and realize them by building the supporting systems that make those futures executable — spanning mobile on-device intelligence, mixed reality frameworks, and spatial telepresence across separate physical spaces. My trajectory here has not been linear: I started as a proud DigiPen Dragons, professional game developer working on Minecraft: Education Edition at Microsoft Studios, then turned to medical imaging and 3D vision researcher during my master's.

Most of computing pulls people into screens. My research asks the opposite — how spatial computing can extend computation into physical space, so that it augments rather than displaces our experience of the real world. Realizing this requires a new kind of software platform: one that moves beyond passively sensing or simulating space, toward systems that interact with users and actuate the environment itself. I see this as a bridge between computer systems and architecture — where built environments are no longer static backgrounds but dynamic structures, co-designed with the computational layer that inhabits them.

Outside of research, I'm an avid yogi who enjoys getting lost in the city and in nature.

2025

Explorable Ideas: Externalizing Ideas as Explorable Environments
Preprint

Explorable Ideas: Externalizing Ideas as Explorable Environments

Euijun Jung, Jingyu Lee, Minji Kim, Youngki Lee

arXiv preprint, 2025.

2024

Logan: Loss-tolerant Live Video Analytics System
Conference

Logan: Loss-tolerant Live Video Analytics System

Kichang Yang, Minkyung Jeong, Juheon Yi, Jingyu Lee, Kyungsoo Park, Youngki Lee

Proceedings of the 31st Annual International Conference on Mobile Computing and Networking, 2024.

Maestro: The Analysis-Simulation Integrated Framework for Mixed Reality
Conference

Maestro: The Analysis-Simulation Integrated Framework for Mixed Reality

Jingyu Lee, Hyunsoo Kim, Minjae Kim, Byung-Gon Chun, and Youngki Lee

Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services, 2024.

Poster: XRMan: Towards Real-time Hand-Object Pose Tracking in eXtended Reality
Poster

Poster: XRMan: Towards Real-time Hand-Object Pose Tracking in eXtended Reality

Dongho Han, Jingyu Lee, Minjae Kim, and Youngki Lee

Proceedings of the 31st Annual International Conference on Mobile Computing and Networking, 2024.

2022

Band: Coordinated Multi-DNN Inference on Heterogeneous Mobile Processors
Conference

Band: Coordinated Multi-DNN Inference on Heterogeneous Mobile Processors

Joo Seong Jeong*, Jingyu Lee*, Donghyun Kim, Changmin Jeon, Changjin Jeong, Youngki Lee, and Byung-Gon Chun

Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services, 2022.

2021

Liver Segmentation in Abdominal CT Images via Auto-Context Neural Network and Self-Supervised Contour Attention
Journal

Liver Segmentation in Abdominal CT Images via Auto-Context Neural Network and Self-Supervised Contour Attention

Minyoung Chung, Jingyu Lee, Sanguk Park, Chae Eun Lee, Jeongjin Lee, and Yeong-Gil Shin

Artificial Intelligence in Medicine, 2021.

ParallelFusion: Towards Maximum Utilization of Mobile GPU for DNN Inference
Workshop

ParallelFusion: Towards Maximum Utilization of Mobile GPU for DNN Inference

Jingyu Lee, Yunxin Liu, Youngki Lee

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning (in conjunction with MobiSys), 2021.

2020

Automatic Registration Between Dental Cone-Beam CT and Scanned Surface via Deep Pose Regression Neural Networks and Clustered Similarities
Journal

Automatic Registration Between Dental Cone-Beam CT and Scanned Surface via Deep Pose Regression Neural Networks and Clustered Similarities

Minyoung Chung, Jingyu Lee, Wisoo Song, Youngchan Song, Il-Hyung Yang, Jeongjin Lee, and Yeong-Gil Shin

IEEE Transactions on Medical Imaging, 2020.

Deeply Self-Supervised Contour Embedded Neural Network Applied to Liver Segmentation
Journal

Deeply Self-Supervised Contour Embedded Neural Network Applied to Liver Segmentation

Minyoung Chung, Jingyu Lee, Minkyung Lee, Jeongjin Lee, and Yeong-Gil Shin

Computer Methods and Programs in Biomedicine, 2020.

Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation
Journal

Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation

Minyoung Chung, Minkyung Lee, Jioh Hong, Sanguk Park, Jusang Lee, Jingyu Lee, Il-Hyung Yang, Jeongjin Lee, and Yeong-Gil Shin

Computers in Biology and Medicine, 2020.

Projects

Band

Band

Project Leader & Main Developer

Open-source Deep-Learning Framework for Heterogeneous Mobile Processors

Somnus

Somnus

Technical Director (Team of 4 programmers, 1 designer, 4 artists and 3 sound designers)

3D puzzle platformer that utilizes perspective illusions to manipulate the environment

2016 E3 College Game Competition Finalist (Top 5)

Rigidbody Constraint-based Physics Simulation

Rigidbody Constraint-based Physics Simulation

Project Leader (Solo Project)

Rigidbody constraint-based physics simulation built from scratch using C++

Bomvoid

Bomvoid

Technical Director

3D third-person view puzzle game built from scratch using C++

Musika

Musika

Gameplay Programmer

2D platformer about some notes which have been kicked out of their place in the music sheet by some false notes and want to go back to their place

Education

Ph.D. in Computer Science and Engineering

Seoul National University, Seoul, Republic of Korea

2020 - Present

M.S. in Computer Science and Engineering

Seoul National University, Seoul, Republic of Korea

2018 - 2020

B.S. in Computer Science in Real-Time Interactive Simulation

DigiPen Institute of Technology, Redmond, Washington, USA

2012 - 2016

Experience

Research Intern, Microsoft Research Asia

Heterogeneous and Extreme Computing (HEX) group, Beijing, China (Virtual)

Advisor: Yunxin Liu & Ting Cao

· Deep learning inference acceleration on mobile GPU (ParallelFusion)
December 2020 – May 2021

Software Engineer, Microsoft

Minecraft Education Edition team, Redmond, Washington, USA

· Developed and maintained Minecraft Education & Minecraft Pocket Edition
· Developed companion apps (Classroom Mode & Code Connection)
· Developed visual programming experiences for K-12 students
(Hour of Code - Minecraft Designer and Code Builder extensions for Scratch X)
September 2016 – May 2017

Services