Preprint
Jul 2026
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight is proposed, a graph-aware vision-language model framework designed to enhance the understanding of molecular images by VLMs and significantly outperforms existing VLMs, molecular LLMs, and task-specific models across multiple chemical visual understanding tasks, achieving a new level of molecular image reason...
Wenda Wang, Yihan Tong, Yuwei Hu et al.
· 0 citations