Changhun Oh

[Sep. 2024 - Dec. 2024]: CS230(System Programming) TA
[Sep. 2023 - Dec. 2023]: CS411(System for Artificial Intelligence) Head TA
[Sep. 2022 - Dec. 2022]: CS230(System Programming) TA

About Me

Hello! I am Changhun Oh, graduate student advised by Prof. Jongse Park.

What I’m Interested are devising IT infrastructure to support those standing on the shoulders of giants, and learning new technologies and tools

[Oct. 2025] Our paper Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration has been accepted to ASPLOS 2026.
[Apr. 2025] Our paper MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization has been accepted to CAL 2025.
[Jul. 2024] Our ISCA paper has been received the Distinguished Artifact Award.
[Mar. 2024] Our paper DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics has been accepted to ISCA 2024.

[Sep. 2024] Ph.D. in Graduate School of AI Semiconductor, KAIST (Advisor: Prof. Jongse Park)
[Aug. 2024] MS in School of Computer, KAIST (Advisor: Prof. Jongse Park)
[Aug. 2022] BS in Computer Science and Engineering, POSTECH

Computer Graphics: Neural Rendering, Gaussian Splatting, Ray Tracing
On-Device Emerging Application Acceleration: Continual Learning, Image Diffusion
Hardware Architecture: CPU (RISC-V), GPU, NPU, and so on

[Jun. 2018 - Aug. 2018] Research Intern, System & Networking Group, Microsoft Research Asia

[Jun. 2024] ISCA 2024 Distinguished Artifact Award
[Dec. 2023] Best TA Award in the Education 4.0Q
[2016 - 2022] Scholar of the National Academic Excellence Scholarship for Science and Engineering, Korea Student Aid Foundation (KOSAF)