I am a second-year Ph.D. student at KAIST advised by Professor Joon Son Chung., and I earned my M.S. from KAIST. My research builds plug-and-play pathways to add new modality channels—currently audio—to pretrained LLMs by bridging the modality gap at the representation level. I am exploring diffusion-based representation transport toward an omni-space to reduce reliance on expensive paired multimodal datasets, with strong interest in audio LLMs and duplex speech-to-speech. Previously, I worked on robust “in-the-wild” speech (bilingual/environmental mismatch), large-scale call-center ASR, and disentangled representation learning.
Advisor: Joon Son Chung (Multimodal AI Lab)
Advisor: Joon Son Chung (Multimodal AI Lab)
