Junhyeok Kim

contact: junhyeok[at]yonsei.ac.kr
CV | Twitter | Google Scholar | LinkedIn

I'm a Ph.D. student at Yonsei University's MIR Lab, advised by Prof. Youngjae Yu. Before this, I received my M.S. in Computer Science from Yonsei University, where I worked under Prof. Seon Joo Kim.

My research goal is to build intelligent systems that truly understand and interact with the real world, much like we do. I'm particularly interested in multimodal large language models, with a focus on multimodal reasoning and video understanding. By integrating multiple modalities, I aim to create more adaptive AI systems capable of interpreting complex visual scenes, handling continuous streams of information, and ultimately engaging with the world as seamlessly as humans do.

Actively looking for internship opportunities in 2025!

Publications

• (Working Title) Real-world Multimodal Egocentric Dataset for Blind and Low Vision People Accessibility-aware Guidance
  Junhyeok Kim et al. (First Author)
  In Submission
  
• EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
  Junhyeok Kim, Min Soo Kim, Jiwan Chung, Jungbin Cho, Jisoo Kim, Sungwoong Kim, Gyeongbo Sim, Youngjae Yu
  NAACL 2025 Findings
  
• Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms
  Seungju Han, Junhyeok Kim, Jack Hessel, Liwei Jiang, Jiwan Chung, Yejin Son, Yejin Choi, Youngjae Yu
  EMNLP 2023 (Oral)
  

Miscellaneous

• I like music and movies.