Unverified50% confidenceFactExact time
SPOOK defines the phenomenon in which a vision encoder's embedding similarity decouples from human-visible semantics when the input deviates from the natural image manifold as the "off-manifold failure mode."
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe off-manifold failure mode exists in both language-aligned multimodal encoders (OpenCLIP) and self-supervised vision encoders (DINOv3), suggesting that this vulnerability may be a shared property of the representation geometry of modern vision encoders.72% similarUnverified视觉幻觉指模型在描述图像时生成与实际视觉内容不符的信息，源于语言模型倾向于用语言先验知识填补视觉信号不明确的空白71% similarUnverifiedThe paper points out that learned expression encodings suffer from severe view bias, i.e., the encoding results unintentionally absorb information about camera viewpoint, lighting, and head orientation.70% similarUnverifiedInterpretable intermediate representations in a vision pipeline (such as keypoint coordinates, segmentation masks, or line polylines) are closer to the raw evidence than the final natural-language interpretation, making manual verification easier.68% similarUnverified负空间设计源于格式塔心理学对人类视觉感知规律的研究67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098382API
curl https://kongchang.com/api/v1/knowledge/claims/1098382MCP
get_claim(id=1098382)