Hi, I’m minkyu kim 👋

I am an AI Researcher at AITRICS, where I specialize in multimodal learning and generative AI. My work focuses on developing advanced artificial intelligence models that integrate various data domains (such as images, text, and audio) to solve real-world challenges. My main goal remains to design AI that assists people in various situations.

Prior to joining AITRICS, I received my M.S. degree in Artificial Intelligence from POSTECH in August 2025. During my time there, I was a member of the POSTECH Efficient Learning Lab (EffL) advised by Prof. Jaeho Lee. I mainly focused on data compression, and my final project was on text-guided image compression. My previous research experience also includes collaborations with Prof. Tae-Hyun Oh on audio captioning and with Prof. Sangpil Kim on event-based photometric stereo.

I earned my B.S. in Electrical and Electronics Engineering from Chung-Ang University (CAU).

Publication 📜

(* means ‘equal contribution’)

Hagyeong Lee*, Minkyu Kim*, Jun-Hyuk Kim, Seungeon Kim, Dokwan Oh, Jaeho Lee, “Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity”, ICML, 2024

Minkyu Kim*, Kim Sung-Bin*, Tae-Hyun Oh, “Prefix tuning for automated audio captioning”, ICASSP (Oral), 2023

Services 💼

• (Peer Review) IEEE/ACM Transactions on Audio, Speech, and Language Processing
• (Military service, 2018.3 ~ 2019.11) Auxiliary Police 👮