Methods paper defines functional regions in visual language models, suggesting measurable anatomy of models.
A Mercury methods paper defining recurring functional regions across 38 visual language-model towers: embed/detokenization, surface, structural, semantic, and output zones. The paper turns the Hope of City skyline into a measurable anatomy using occupancy, transition sharpness, cross-model stability, and boundary uncertainty. Copyright (c) 2026 Chen, Ho Yiing (norika). Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).
No takes yet. Share an insight, caveat, or question.
Ho Yiing Chen (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: