About

I am a Ph.D. student advised by Youngki Lee at the Human-Centered Computer Systems Lab. My research interest lies in designing real-time pipelines that combine simulation, deep learning, and visual algorithms for dynamic scene understanding in XR.

Interests
  • Dynamic Scene Understanding for XR
  • On-Device AI Systems
  • Synthetic Data Generation
Education

  • Ph.D. in Computer Science and Engineering

    Seoul National University, Mar 2020 - present

  • B.S. in Computer Science and Engineering

    Seoul National University, Mar 2014 - Feb 2020

  • B.S. in Mechanical Engineering

    Seoul National University, Mar 2014 - Feb 2020

Projects

*
All On-Device AI Sensing On-Going
TinyMem

TinyMem

Memory-efficient multi-DNN inference on tiny AI accelerators with weight memory virtualization

Mondrian

Mondrian

On-device high-throughput video analytics on mobile devices with compressive packed inference

Band

Band

Multi-DNN inference framework for heterogeneous mobile processors with subgraph-level scheduling

VSense

VSense

Overcoming small size limitation of real-world activity recognition datasets with synthetically generated data

FallSim

FallSim

Enabling real-world fall detection with synthesized fall motions from physics simulations

Publications

Changmin Jeon, Taesik Gong, Juheon Yi, Fahim Kawsar, Chulhong Min (2025). TinyMem: Boosting Multi-DNN Inference on Tiny AI Accelerators with Weight Memory Virtualization. HotMobile 2025.

PDF Cite

Changmin Jeon, Seonjun Kim, Juheon Yi, Youngki Lee (2024). Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inference. arXiv 2024.

PDF Cite Code

Joo Seong Jeong, Jingyu Lee, Donghyun Kim, Changmin Jeon, Changjin Jeong, Youngki Lee, Byung-Gon Chun (2022). Band: Coordinated Multi-DNN Inference on Heterogeneous Mobile Processors. MobiSys 2022.

PDF Cite Code Project Video