Jeongeun Lee
About Me
I am a final-year M.S. student in the Data & Language Intelligence (DLI) Lab at Yonsei University, advised by Prof. Dongha Lee. I am also fortunate to work closely with the Computational Intelligence & Photography Lab (CIPLAB) under the guidance of Prof. Seon Joo Kim. Previously, I received my B.S. in Computer Science from Yonsei University.
If you’re interested in collaborating on research or exploring new ideas together, please feel free to connect with me anytime!
Research Interest
I aim to build human-supportive AI that can understand and assist people in dynamic, real-world environments. During my master’s, I explored how (M)LLMs can leverage long-term multimodal context across several directions, including:
- personalization in text-to-image generation and video highlight detection
- agentic frameworks that simulate real-world user behaviors for proactive assistance
- personalized embodied agent that leverage long-term human-agent interactions for instruction understanding and planning
More recently, I have become interested in how AI agents can learn from continuous input streams to build persistent knowledge about users and the world. In particular, I am interested in:
- learning about users, their activities, and their situational context from egocentric experience
- building and updating persistent knowledge of the physical world to support personalized reasoning, decision-making, and action
News
is accepted to ECCV 2026 🇸🇪
is accepted to COLM 2025 🇨🇦Publications
*: denotes equal contribution.
-
ECCV
European Conference on Computer Vision (ECCV), 2026. -
EMNLP Findings
Empirical Methods in Natural Language Processing (EMNLP) Findings, 2025. -
COLM
Conference on Language Modeling (COLM), 2025. -
ICLR Workshop
ICLR Workshop on Reliable and Responsible Foundation Models, 2024.
arXiv
arXiv
Powered by Jekyll and Minimal Light theme.