Vibe空间：创意连接与表达视觉概念
Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
提出在CLIP特征空间中学习层次图流形以获取低维测地线，实现远距离视觉概念间的平滑语义过渡，为概念混合与创意生成提供可复用的几何路径规划方法。
原文依据 We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP
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建新的视觉概念通常需要通过不同概念之间最相关的共享属性——即它们的“氛围”（vibe）——来建立连接。我们引入了Vibe混合（Vibe Blending），这是一项新颖的任务，旨在生成连贯且有意义的混合体，从而揭示图像之间的这些共享属性。当前方法难以实现这样的混合，因为它们难以识别并遍历潜变量空间中连接远距离概念的非线性路径。我们提出了Vibe空间（Vibe Space），这是一种层次图流形，能够在CLIP等特征空间中学习低维测地线，从而实现概念之间平滑且语义一致的过渡。为了评估创意质量，我们设计了一个受认知启发的框架，结合了人类判断、LLM推理以及基于几何路径的难度分数。我们发现，Vibe空间生成的混合体在人类评价中始终比当前方法更具创意且更连贯。
英文原文摘要 901 字符
Creating new visual concepts often requires connecting distinct ideas through their most relevant shared attributes--their vibe. We introduce Vibe Blending, a novel task for generating coherent and meaningful hybrids that reveals these shared attributes between images. Achieving such blends is challenging for current methods, which struggle to identify and traverse nonlinear paths linking distant concepts in latent space. We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP, enabling smooth and semantically consistent transitions between concepts. To evaluate creative quality, we design a cognitively inspired framework combining human judgments, LLM reasoning, and a geometric path-based difficulty score. We find that Vibe Space produces blends that humans consistently rate as more creative and coherent than current methods.