2026 CVPR See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis Jaehyun Park* , Minyoung Ahn*, Minkyu Kim, and 3 more authors 2026 PDF Code Website 2025 ICLR Active Learning for Continual Learning: Keeping the Past Alive in the Present Jaehyun Park , Dongmin Park, and Jae-Gil Lee† In The Thirteenth International Conference on Learning Representations, 2025 2024 NeurIPS Exploiting Representation Curvature for Boundary Detection in Time Series Yooju Shin, Jaehyun Park , Susik Yoon, and 3 more authors In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024 PDF