Chaeyun Kim
About Me
I obtained my M.S. in Data Science from Seoul National University's Visual Information Processing Lab, advised by Prof. Joonseok Lee.
Long-term Goal: Transforming multimodal LLMs into systems that are controllable, interpretable, and safe — mechanisms that generalize across modalities, languages, and deployment contexts.
Research Interests
- Interpretability, Robustness, and Alignment
- Reasoning & Grounding: Spatial-geometric reasoning and multimodality
- AI Safety: Jailbreak methods, AI Guardrail, AI Red-teaming
News
- [Feb. 2026] One paper about multimodal object hallucination evaluation accepted to CVPR 2026.
- [Jan. 2026] One paper about culturally adaptive red-teaming accepted to ICLR 2026.
- [Jan. 2026] One paper about motion-aware referring image segmentation accepted to AISTATS 2026.
- [Mar. 2025] Started working at Selectstar as AI Researcher.
- [Jul. 2024] One paper about referring image segmentation accepted to ECCV 2024.
- [Sep. 2022] Started M.S. in Data Science at Seoul National University.
Publications
-
CVPR 2026
Fine-Grained Multi-Image Object Hallucination BenchmarkIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.Coming Soon -
ICLR 2026
International Conference on Learning Representations (ICLR), 2026. -
AISTATS 2026
International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. -
ECCV 2024
European Conference on Computer Vision (ECCV), 2024.
Experience
Education
M.S., Data Science (Visual Information Processing Lab), Seoul National University, Feb. 2025 B.S., International Relations, Seoul National University, Feb. 2022 Exchange Student, University of Washington, Seattle, Jan. 2020 – Jul. 2020
Work Experience
Selectstar, AI Researcher (Mar. 2025 – Dec. 2025)
Services
Conference Reviewers
International Conference on Machine Learning (ICML) 2026 Knowledge Discovery and Data Mining (KDD) 2026
Powered by Jekyll and Minimal Light theme.