visual-anchor

Tag

Cards List
#visual-anchor

ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding

arXiv cs.AI · 2026-05-19 Cached

ChemVA is a framework that addresses the visual and semantic bottlenecks in LLMs for understanding chemical reaction diagrams, achieving 92% structural recognition accuracy and consistent ~20 percentage point gains across nine LLMs.

0 favorites 0 likes
← Back to home

Submit Feedback