I am a second-year Ph.D. student at KAIST, where I also received my M.S. degree, under the supervision of Professor Joon Son Chung. My research focuses on building efficient and reliable multimodal AI systems that can perceive, reason, and generate across vision, audio, and language.
My recent work explores both multimodal representation learning and the efficiency of multimodal models, from token compression for omni-modal LLMs and parameter-/memory-efficient audio-visual learning to multimodal understanding and generation tasks such as joint audio-video generation, audio-visual captioning, active speaker detection, and talking-face generation. I am particularly interested in bridging fundamental multimodal learning with practical AI applications, including real-time multimodal assistants, video understanding, human-AI interaction, and generative content creation.
Ph.D. in Electrical Engineering (Advisor: Joon Son Chung)
M.S. in Electrical Engineering (Advisor: Joon Son Chung)
B.S. in Electrical Engineering (Magna Cum Laude)
AI Research Intern (Advisor: Seungkwon Kim)
Research Officer (Military Service; Discharged as First Lieutenant, Republic of Korea Army. Advisor: Youngjung Kim)
Research Assistant (Advisor: Steven Euijong Whang)
