SOURCE-LINKED INTELLIGENCE

Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representation contain? We use canonical color as a controlled test case to ask whether vision encoders make canonical-color information linearly accessible, even when color is removed from the input image. We construct a dataset of objects with canonical colors, and probe vision encoders for both color and object identity using color and grayscale images. We find that canonical color remains decodable from grayscale images, and

Read original source ↗ Open in workspace

recordType

paper

region

Global