Dayoon Ko

- Ph.D. Student

Introduction

Hello, I’m M.S./Ph.D integrated student in CSE at Seoul National University advised by Prof. Gunhee Kim.
My primary research interest is Audio-Visual learning and Video representation learning.

Contact

dayoon.ko@vision.snu.ac.kr

Education

M.S. : Department of Computer Science and Engineering, Seoul National University, 2022~
B.S. : Department of Computer Science and Engineering, Yonsei University, 2022

Publication

• Dayoon Ko, Jinyoung Kim, Sohyeon Kim, Jinhyuk Kim, Jaehoon Lee, Seonghak Song, Minyoung Lee and Gunhee Kim, GradNormIR: When Should We Update the Dense Retriever in Evolving Corpora?, ACL 2025 (Findings).
• Jaewoo Ahn, Heeseung Yun, Dayoon Ko and Gunhee Kim, Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates, ACL 2025.
• Jinyoung Kim, Dayoon Ko and Gunhee Kim, DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG, EMNLP 2024.
• Dayoon Ko, Jinyoung Kim, Hahyeon Choi and Gunhee Kim, GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?, ACL 2024.
• Dayoon Ko, Sangho Lee and Gunhee Kim, Can Language Models Laugh at YouTube Short-form Videos?, EMNLP 2023.