Scholar
Junwon Lee
Google Scholar ID: aJ-InM0AAAAJ
KAIST
Controllable Audio Generation
Multimodal Learning
Music Information Retrieval
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
110
H-index
6
i10-index
5
Publications
11
Co-authors
8
list available
Contact
No contact links provided.
Publications
10 items
Improving Text-to-Music Generation with Human Preference Rewards
2026
Cited
0
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
2026
Cited
0
AdaTT: Text-Guided Instrument Timbre Transfer with Target-Adaptive Structural Control
2026
Cited
0
CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
2026
Cited
0
AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents
2026
Cited
0
UNMIXX: Untangling Highly Correlated Singing Voices Mixtures
2026
Cited
0
Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
2025
Cited
0
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation
2025
Cited
0
Load more
Resume (English only)
Co-authors
8 total
Juhan Nam
KAIST
Keunwoo Choi
talkpl.ai
Yoonjin Chung
Gaudio Lab.
Seungheon Doh
talkpl.ai
Jaekwon Im
KAIST
Co-author 6
Gyubin Lee
KAIST
Hounsu Kim
Korea Advanced Institute of Science and Technology
