Yunsu Kim
Ph.D. student, Changwon National University
I work on signal processing — underwater acoustics, sonar classification, machine fault diagnosis, and metocean forecasting — as well as agentic AI systems for analysis, decision-making, and research workflows. By combining domain knowledge from real-world signal processing problems with agentic AI, I aim to build AI systems that are both reliable and practically useful.
Selected publications
see all →Career highlights
- to Present
Ph.D. Candidate, Information and Communication Engineering @ Changwon National University · Changwon, South Korea
- to 2023
Course Instructor @ Industry-Academic Convergence Technology Education Center, Changwon National University · Changwon, South Korea
Metaverse Platform Development and AI Technology Training — fundamentals of programming, machine learning and deep learning in Python.
- to 2022
Course Instructor @ Industry-Academic Convergence Technology Education Center, Changwon National University · Changwon, South Korea
Smart Factory Supplier IT Specialist Training Program — fundamentals of programming, machine learning and deep learning in Python.
- to
M.S. in Information and Communication Engineering @ Changwon National University · Changwon, South Korea
Latest posts
-
Agent Harness #5 — Where the Human Goes
The pipeline stopped to ask a person at five gates. The gates worked; the log could not say who answered. Every verified run's plan was approved by a script in under two seconds.
Yunsu Kim -
Agent Harness #4 — Letting a Model Write Code You Then Run
Phase 2 let a model write the experiment code. Deciding which files it may write was the right idea, half-built. The check that guarded execution skipped every file importing numpy.
Yunsu Kim -
Agent Harness #3 — The Handoff Problem
Two channels crossed every phase boundary: the handoff the next stage reads, and the event stream I read. I typed both and enforced neither.
Yunsu Kim