Synapse Open Synapse
Biology

Vision-Language Models Reproduce a Human Mental-Extrapolation Bias in the Watanabe Illusion

arXiv q-bio · · 1 min read

arXiv:2611.17741v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for visual judgments, yet whether they share human perceptual biases, and where in the model such biases arise, is unclear.

Latest from arXiv q-bio