MolSight integrates a Molecular Topology Module and Molecular Grounding Module into VLMs to enhance molecular image understanding and claims to outperform prior models on chemical visual tasks.
2024 International Joint Conference on Neural Networks (IJCNN) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight integrates a Molecular Topology Module and Molecular Grounding Module into VLMs to enhance molecular image understanding and claims to outperform prior models on chemical visual tasks.