Hyunho Yeo

hyunho.yeo@kaist.ac.kr | Google Scholar | Linkedin | CV


I am a final-year Ph.D. student in Electrical Engineering at KAIST advised by Professor Dongsu Han. I am currently looking for a tech company located in the Bay Area or Seattle or Seoul.

I have worked on AI/ML and video systems for over six years, publishing papers at top-tier system conferences such as OSDI, SIGCOMM, and MobiCom. I learned skills to build large-scale ML systems and utilize several ML frameworks (e.g., PyTorch, Tensorflow, TensorRT). I also have a vast repository of in-depth knowledge about video codec internals and video streaming algorithms/systems. More specifically, I’ve focused on two different directions. First, I developed ML-powered video streaming that applies neural quality enhancement to obtain high-definition video from lower-quality transmission. Second, I built resource-efficient training and inference frameworks to enable ML-powered video streaming on larger scales.

selected publications (see all)

    NeuroScaler: Neural Video Enhancement at Scale
    Hyunho Yeo, Hwijoon Lim, Jaehong Kim, Youngmok Jung, Juncheol Ye, and Dongsu Han
    In Proceedings of the ACM SIGCOMM 2022 conference Aug 2022
  2. MobiCom
    NEMO: Enabling Neural-Enhanced Video Streaming on Commodity Mobile Devices
    Hyunho Yeo, Chan Ju Chong, Youngmok Jung, Juncheol Ye, and Dongsu Han
    In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking Aug 2020
    Neural-Enhanced Live Streaming: Improving Live Video Ingest via Online Learning
    Jaehong Kim^, Youngmok Jung^,  Hyunho Yeo, Juncheol Ye, and Dongsu Han
    In Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication Aug 2020
  4. OSDI
    Neural Adaptive Content-aware Internet Video Delivery
    Hyunho Yeo, Youngmok Jung, Jaehong Kim, Jinwoo Shin, and Dongsu Han
    In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) Oct 2018