Se Jin Park

I'm a final-year Ph.D. student at KAIST, Integrated Vision and Language Lab (IVLLab), advised by Professor Yong Man Ro. My research focuses on advancing multimodal human-AI interactions—integrating audio, vision, and text—based on Large Language Models. Specifically, I have worked on multimodal integration, unbounded generation, generation fidelity, and full-duplex behaviors for realistic and engaging human-AI dialogues. 

Email: jinny960812@kaist.ac.kr 

 CV | Google Scholar | LinkedIn