Hello! I’m Minyoung Kim. I am currently a undergraduate student at Korea University and a research intern of ALIN Lab at KAIST, advised by Prof. Jinwoo Shin.

My research goal is to develop a general-purpose AI system that understands the physical world and interacts with it. I am particularly interested in building general world models that maintain internal and temporal consistency and leveraging such models to enable interaction with the environment. I am also open to exploring emerging research areas that could contribute to the development of more general AI systems.

About me

🎓 I am a passionate undergraduate researcher at Korea University, majoring in Computer Science.
🎓 I am a research intern of ALIN-lab at KAIST.
💡 I love exploring cutting-edge technologies like World Model, Vision-Language-Action, Generative Model and Digital Watermarking.
🌱 Currently, I’m diving deeper into World Model and Vision-Language-Action.

🔥 News

2026.02: 🎉🎉 One paper has been accepted by CVPR 2026 Findings.
2025.05: 🎉🎉 One paper has been accepted by Interspeech 2025.
2025.05: 🎉🎉 One paper has been accepted by ACL 2025.

🎓 Education

[2023.03.01 ~ Present] B.S. in Computer Science and Engineering, Korea University

💻 Experience

[2026.03 ~ Present] Research Intern, Algorithmic Intelligence Laboratory (ALIN), KAIST (Advised by Prof. Jinwoo Shin)
[2024.08 ~ 2026.02] Research Intern, Multimodal Interactive Intelligence Lab (MIIL), Korea University (Advised by Prof. Paul Hongsuck Seo)

🎖 Honors and Awards

[2023.11.25 ~ 2023.11.26] 2nd Place, 2023 iNThon
[2024.07.01 ~ 2024.08.06] Corporate Sponsorship Award, 2024 SW-Centered University Digital Competition (AI Category)

📝 Publications

CVPR 2026 Findings Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
Minyoung Kim Paul Hongsuck Seo

Interspeech 2025 Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries
Minyoung Kim Sehwan Park Sungmin Cha Paul Hongsuck Seo

ACL 2025 ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
Dosung Lee* Wonjun Oh* Boyoung Kim Minyoung Kim Joonsuk Park† Paul Hongsuck Seo†