Unverified50% confidenceFactExact time
Most vision-language models process CT scans as a stack of flat images, sampling only a few slices or compressing volumetric data into a small number of tokens, causing critical spatial details to be lost before inference.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMultimodal large models split images into fixed patches, convert them into high-dimensional vectors via a visual encoder (based on the ViT architecture), and align them to the language model's token embedding space—this is inference, not reading.74% similarUnverifiedThin linear objects occupy very few pixels in a frame, making it easy for models to forget or redraw them during frame-by-frame generation, causing lines to flicker, distort, or change in number.73% similarUnverified对于需要精确视觉推理的场景（文档理解、图表问答、机器人视觉、医学影像），单靠CLIP视觉编码器不够，建议在视觉编码器层面做增强而非仅依赖更大的语言模型73% similarVerifiedCLIP is capable of semantically composing different visual features in vector space through compositional generalization, even when the exact description never appeared in the training data.72% similarUnverifiedLarge models perform inferential completion of image content, which in OCR tasks can lead to hallucinatory recognition—reading in characters that do not actually exist—creating a contradiction with document entry scenarios that require high fidelity.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989942API
curl https://kongchang.com/api/v1/knowledge/claims/989942MCP
get_claim(id=989942)