See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
Published in CVPR 2026, 2026
Recommended citation: Jaehyun Park, Minyoung Ahn, Minkyu Kim, Jonghyun Lee, Jae-Gil Lee, Dongmin Park. "See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis." CVPR 2026.