Hi! I'm Joohyung Yun, a 3rd year integrated M.S./Ph.D. student in Computer Science at POSTECH, advised by Professor Wook-Shin Han in the Data Systems Lab. My research sits at the intersection of Natural Language Processing and Information Retrieval, with a focus on Retrieval-Augmented Generation (RAG) for complex, real-world documents.
I'm particularly interested in multimodal document RAG: collections that mix text, tables, and images. My recent projects explore multihop reasoning across these modalities and how to combine retrieval with LLM reasoning effectively. This includes late-interaction retrieval over structured components and multi-granular fusion strategies that blend table–text evidence with LLM inference.
Before turning to RAG, I worked on efficient schema discovery from JSON documents, which led to a first-author publication at PVLDB. I completed my B.S. at POSTECH summa cum laude and previously spent a summer as a full-stack developer at SK hynix.
Contact: jhyun@dblab.postech.ac.kr · joohyung00@postech.ac.kr
Research Focus
I'm currently working on methods and systems for:
- Multimodal & multihop retrieval over documents composed of text, tables, and images
- RAG architectures for reliable QA over multimodal documents
News
LILaC accepted to appear at EMNLP 2025 (Suzhou, China)
HELIOS to appear at ACL 2025 (Vienna, Austria)
ReCG accepted to PVLDB on JSON schema discovery
Team dRAGonRAnGers: 1st in comparison & post-processing tests at KDD Cup RAG
I started integrated M.S./Ph.D. at POSTECH (Data Systems Lab)!
Publications
-
Conference
Yun, J., Lee, D., Han, W.
EMNLP, 2025. -
Conference
Park, S., Yun, J., Lee, J., Han, W.
ACL, 2025. -
Workshop
Park, S., Seok, J., Lee, J., Yun, J., Lee, W.
KDD Cup Workshop on Retrieval-Augmented Generation, 2024. -
Journal
Yun, J., Tak, B., Han, W.
PVLDB, 2024.
Email: jhyun@dblab.postech.ac.kr · joohyung00@postech.ac.kr