Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion

Open paper
Benchmark Model Rank Results
molecule-captioning-on-l-m-24Mol2Lang-VLM#1BLEU-2: 77.7BLEU-4: 56.3ROUGE-1: 78.6ROUGE-2: 59.1ROUGE-L: 56.5…
molecule-captioning-on-chebi-20Mol2Lang-VLM#10BLEU-2: 61.2BLEU-4: 52.7METEOR: 63.3ROUGE-1: 67.4ROUGE-2: 53.2…

Rank counts only results with a code link.