avatar

Jeho Lee

Ph.D. Student
Yonsei University
jeholee (at) yonsei.ac.kr


About Me

I am a Ph.D. candidate (exp. Feb 2027) at Yonsei University, advised by Prof. Hojung Cha.

I develop system software for efficient on-device AI inference, with a focus on mobile NPUs and heterogeneous mobile SoCs. To address the challenges of accelerating on-device inference on resource-constrained platforms, I take the following approaches:

Selected Publications

* Co-first author

  1. [ACM EuroSys 2026] viNPU: Optimizing Vision Transformer Inference on Mobile NPUs
    Jeho Lee, Gunjoong Kim, Chanyoung Jung, Jaehee Kim, Seonghoon Park, Hojung Cha
  2. [ACM MobiSys 2025] ARIA: Optimizing Vision Foundation Model Inference on Heterogeneous Mobile Processors for Augmented Reality
    Chanyoung Jung*, Jeho Lee*, Gunjoong Kim, Jiwon Kim, Seonghoon Park, Hojung Cha
    🏆 Best Paper Award (2/233) | Invited to ACM GetMobile
  3. [ACM MobiCom 2024] Panopticus: Omnidirectional 3D Object Detection on Resource-constrained Edge Devices
    Jeho Lee, Chanyoung Jung, Jiwon Kim, Hojung Cha

News

Earlier news
  • [Jan. 2026] Our paper (ARIA @ MobiSys25) has been invited to ACM GetMobile.
  • [Jan. 2026] Our paper has been accepted to ACM TECS.
  • [Aug. 2025] Two papers have been accepted to ACM MobiCom 2025.
  • [Jul. 2025] Two papers have been accepted to ACM EMSOFT 2025.
  • [June. 2025] Our paper (ARIA) won the Best Paper Award 🏆 at ACM MobiSys 2025.
  • [May. 2025] I am selected as one of Rising Stars at ACM MobiSys 2025 and received SIGMOBILE Student Travel Grant for attending MobiSys 2025.
  • [Apr. 2025] Our paper has been accepted to ACM MobiSys 2025.
  • [Jul. 2024] Our paper has been accepted to ACM MobiCom 2024.
  • [Dec. 2023] Our paper has been accepted to IEEE INFOCOM 2024.
  • [May. 2023] Our paper has been accepted to ACM MobiSys 2023.
  • [Dec. 2022] Our paper has been accepted to IEEE INFOCOM 2023.

Publications

Conference and Journal

  1. [ACM EMSOFT 2026] DynaStitch: Dynamic ViT Inference via Neural Stitching for Resource-Constrained Edge Devices
    Jiwon Kim, Luca Mottola, Jeho Lee, Seonghoon Park, Hojung Cha, Thiemo Voigt
  2. [ACM TECS] Phoenix: Thermal-Aware On-device Inference of Multi-Instance DNNs for Mobile Video Applications
    Seunghyeok Jeon, Jiwon Kim, Jeho Lee, Hojung Cha
  3. [ACM MobiCom 2025] Vega: Fully Immersive Mobile Volumetric Video Streaming with 3D Gaussian Splatting
    Gunjoong Kim*, Seonghoon Park*, Jeho Lee, Chanyoung Jung, Hyungchol Jun, Hojung Cha
  4. [ACM MobiCom 2025] EOS: Energy-Optimized Super-Resolution on Mobile Devices for Live 360-Degree Videos
    Seonghoon Park, Minchan Kim, Hyejin Park, Jeho Lee, Jiwon Kim, Hojung Cha
  5. [ACM EMSOFT 2025] Ember: Task Wakeup Sequence–Based Energy Optimization for Mobile Web Browsing
    Seonghoon Park, Jiwon Kim, Jeho Lee, Hojung Cha
  6. [ACM EMSOFT 2025] SecureRide: Detecting Safety-threatening Behavior of E-Scooters Using Battery Information
    Jiwon Kim, Geon Kim, Jeho Lee, Thiemo Voigt, Hojung Cha
  7. [IEEE INFOCOM 2024] Vulture: Cross-Device Web Experience with Fine-Grained Graphical User Interface Distribution
    Seonghoon Park, Jeho Lee, Yonghun Choi, Hojung Cha
  8. [ACM MobiSys 2023] OmniLive: Super-Resolution Enhanced 360° Video Live Streaming for Mobile Devices
    Seonghoon Park*, Yeonwoo Cho*, Hyungchol Jun, Jeho Lee, Hojung Cha
  9. [IEEE INFOCOM 2023] Crow API: Cross-device I/O Sharing in Web Applications
    Seonghoon Park, Jeho Lee, Hojung Cha

Short Papers, Posters, & Highlights

  1. [ACM GetMobile] 3DGS on Your Phone: Towards Fully Immersive Mobile Volumetric Video Streaming
    Gunjoong Kim*, Seonghoon Park*, Jeho Lee, Chanyoung Jung, Hyungchol Jun, Hojung Cha
  2. [ACM GetMobile] VFM in Your Hands: Optimizing Real-Time Scene Understanding for Mobile Augmented Reality
    Jeho Lee*, Chanyoung Jung*, Gunjoong Kim, Jiwon Kim, Seonghoon Park, Hojung Cha
  3. [ACM MobiSys 2025 Rising Stars Forum] Towards Accurate, Adaptive, and Real-time Machine Perception on Resource-constrained Platforms
    Jeho Lee
  4. [ACM MobiSys 2025 Poster] Poster: Mixture of Class-aware Experts for Efficient AIoT Inference
    Hyemin Jeong, Jeho Lee, Seunghyeok Jeon, Hojung Cha

Awards and Honors

Academic Service


Powered by Jekyll and Minimal Light theme.