CREward：一种按类型划分的创意奖励模型
CREward: A Type-Specific Creativity Reward Model
提供了一种按类型（几何/材质/纹理）分解的创意奖励模型，可直接作为扩散或生成模型的偏好奖励信号，并通过 LoRA 微调引导生成更具创意的图像；其用 LVLM 标注替代人工标注构建奖励模型的流程也可迁移到其他主观属性（如美学、风格）的奖励建模。
原文依据 we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论创意是一种复杂的现象。在表示和评估创意时，将其视为单一且不加区分的量显得天真且缺乏说服力。在本工作中，我们学习了首个按类型划分的创意奖励模型，命名为 CREward，它涵盖三个创意「轴」——几何、材质与纹理，使我们得以从图像成像流程的视角审视创意。为构建该奖励模型，我们首先开展了一项人类基准评测，以捕捉人类对各类创意图像中每种创意类型的感知。随后，我们分析了人类判断与大型视觉语言模型（LVLM）预测之间的相关性，确认 LVLM 与人类感知表现出高度对齐。基于这一观察，我们收集 LVLM 生成的标签来训练 CREward 模型，该模型可同时用于创意图像的评估与生成。我们探索了 CREward 的三项应用：创意评估、可解释创意，以及面向人类设计灵感与通过低秩适配引导创意生成的创意样本获取。
英文原文摘要 1142 字符
Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and under-whelming. In this work, we learn the first type-specific creativity reward model, coined CREward, which spans three creativity "axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.