Ying Huang

Traditional aesthetic assessment models miss the mark by relying on static scores, while RED-Aes reveals the dynamic, comparative nature of human aesthetic perception for superior generalization.

SIGMA closes the structural and distributional gaps in Vision Foundation Model adaptation, achieving state-of-the-art performance in dense prediction tasks with minimal trainable parameters.

Stop optimizing generative engines in isolation: MAGEO learns reusable editing strategies that dramatically improve visibility and citation fidelity across diverse engines.