Unverified50% confidenceFactExact time
The study uses two datasets: SilCC (which modulates naming difficulty through progressively complex abstract shape compositions) and PixCC (which increases recognition difficulty by adding random visual noise) to compare the associative creativity of humans and multimodal large models.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHumans still significantly outperform multimodal large models in associative creativity, especially when facing visual stimuli that are difficult to name, where humans can produce more diverse and more original descriptions.69% similarUnverifiedIn the PixCC dataset, humans showed a strategy shift: from holistic semantic association to describing low-level visual attributes (such as color and texture), whereas MLLMs tended to adhere to semantic-level association.67% similarUnverifiedCLIP establishes semantic mappings between text descriptions and visual features through contrastive learning on hundreds of millions of image-text pairs, guiding the denoising process of diffusion models.67% similarUnverified细粒度视觉识别任务的核心挑战是类间差异极小、类内变化很大64% similarUnverifiedUsing visual material with strong collective memory as a test benchmark is a common AI capability evaluation method, as it anchors the judging criteria to similarity with the original work rather than subjective aesthetics.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079452API
curl https://kongchang.com/api/v1/knowledge/claims/1079452MCP
get_claim(id=1079452)