Our paper is accepted to Conference on Computer Vision and Pattern Recognition (CVPR-26) 🎉.
This paper introduces CREward, a type-specific reward model that evaluates and guides image creativity across three distinct axes—geometry, material, and texture—by leveraging Large Vision-Language Models (LVLMs) aligned with human perception.
Title: CREward: A Type-Specific Creativity Reward Model
Authors: Jiyeon Han, Ali Mahdavi-Amiri, Hao Zhang, and Haedong Jeong
Pre-print version:
CREward: A Type-Specific Creativity Reward Model
Accepted version:
(To appear)