| Paper | Code | BLEU-2 | BLEU-4 | ROUGE-1 | ROUGE-2 | ROUGE-L | METEOR | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|
| Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion | ✓ Link | 77.7 | 56.3 | 78.6 | 59.1 | 56.5 | 74.1 | Mol2Lang-VLM | 2024-08-15 |
| XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks | ✓ Link | 77.4 | 56.0 | 78.9 | 59.4 | 56.8 | 73.8 | XMolCap | 2025-05-23 |
| Translation between Molecules and Natural Language | ✓ Link | 76.9 | 55.6 | 77.7 | 58.0 | 55.7 | 74.3 | MolT5-Large | 2022-04-25 |
| []() | 73.81 | 53.04 | 80.06 | 60.17 | 57.5 | 77.45 | Nach0 | ||
| Translation between Molecules and Natural Language | ✓ Link | 73.8 | 53.5 | 75.0 | 55.9 | 53.9 | 71.8 | MolT5-Base | 2022-04-25 |
| Translation between Molecules and Natural Language | ✓ Link | 70.9 | 51.2 | 74.5 | 55.8 | 54.4 | 70.1 | MolT5-Small | 2022-04-25 |