DPA-MoE accepted to Findings of EMNLP 2026
Our runtime precision control framework for MoE inference was accepted to Findings of EMNLP 2026 — my first paper, and one I led end to end.
Notes, mostly on serving models and the plumbing around them.
Our runtime precision control framework for MoE inference was accepted to Findings of EMNLP 2026 — my first paper, and one I led end to end.
Add+i, the air-gapped full-stack generative AI platform I built at the Agency for Defense Development, moved from beta into full operation.
Commissioned as a lieutenant in the Republic of Korea Air Force, serving as a research officer at the Agency for Defense Development.
Finished a B.S. in Computer Science and Engineering at Seoul National University, summa cum laude.
Started as a programming intern at KRAFTON, splitting time between LLM service development and on-device model serving for inZOI.