Junwon Lee 이준원
I am a Ph.D. student at KAIST Music and Audio Computing Lab advised by Prof. Juhan Nam.
My research focuses on audio-centric multimodal understanding and generative AI technologies for content creators.
Recently, I have been particularly interested in controllable and interactive audio generation that leverages the reasoning, generative, and agentic capabilities of multimodal LLMs.
Previously, I was a research intern at NAVER AI Lab and Gaudio Lab.
Experience
Naver AI Lab
Research Intern, Audio-Visual-Text Generation
Advisor: Jiyoung Lee, Sanghyuk Chun
Seongnam, Korea | Dec 2024 - Feb 2025
Gaudio Lab
Reseaerch Intern, DCASE Challenge on Text-to-Audio Gen. (Part-time)
Advisor: Keunwoo Choi
Seoul, Korea | Nov 2023 - Jun 2024
Bookend
Reseaerch Intern, GPT related product (Part-time)
Daejeon, Korea | Nov 2022 - Feb 2023
AudAI
Intern, Web FrontEnd Dev (SolidJS) and Branding (Part-time)
Advisor: Soonbeom Choi
Daejeon, Korea | Sep 2022 - Feb 2023
Inbody
Research Intern, Computer Vision & Deep Learning related R&D
Future Lab, Seoul, Korea | Sep 2021 - Feb 2022
Music and Audio Computing Lab
Research Intern (Individual Study), Beat tracking, Playlist Captioning
Advisor: Taejun Kim, Seungheon Doh, Prof. Juhan Nam
KAIST (Korea Advanced Institute of Science and Technology) | Sep 2020 - Aug 2021, Jan 2022 - Dec 2022
Data Intelligence Lab
Research Intern (Individual Study), Fairness in ML
Advisor: Kihyun Tae, Yuji Roh, Prof. Steven Euijong Whang
KAIST (Korea Advanced Institute of Science and Technology) | Jul 2020 - Aug 2020, Mar 2021 - Jun 2021
Education
KAIST (Korea Advanced Institute of Science and Technology)
PhD in Graduate School of AI
Music and Audio Computing Lab | Prof. Juhan Nam
2025 - present
KAIST (Korea Advanced Institute of Science and Technology)
MSc in Graduate School of AI
Music and Audio Computing Lab | Prof. Juhan Nam
2023 - 2024
KAIST (Korea Advanced Institute of Science and Technology)
B.S. in Electrical Engineering (Summa Cum Laude)
2018 - 2022
Academic Service, Talk
Reviewer
Conferences: ICASSP, Interspeech
Journals: IEEE TASLP, IJCV
Workshops: ISMIR NLP4MUSA, WASPAA, NeurIPS AI4Music
Organizing Committee
ISMIR 2025, KSMI 2025, DCASE Challenge Task 7 2024.
Talks
Hear what matters! Text-conditioned selective video-to-audio generation, KSMI Post-ICML Workshop | 7/13, 2026
Controllable Audio Generation with Multimodal Conditions, Multimodal AI Lab, Ewha Womans University | 2/19, 2026
Award & Honors
Dean’s List
The School of Freshman, KAIST | Spring and Fall, 2018.
School of Electrical Engineering, KAIST | Fall, 2019.
The National Scholarship for Science and Engineering
Korea Student Aid Foundation | 2020-2021