Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
arXiv:2610.06928v1 Announce Type: new Abstract: We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a metonymic grounding mechanism in which abstract predictions are driven by concrete, interpretable…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-07 04:00 · arXiv cs.AI
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers