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

Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion Duong Thanh Tran author Nhat Truong Pham author Nguyen Doan Hieu Nguyen author Balachandran Manavalan author 2024-08 text Proceedings of the 1st Workshop on Language + Molecules (L+M 2024) Carl Edwards editor Qingyun Wang editor Manling Li editor Lawrence Zhao editor Tom Hope editor Heng Ji editor Association for Computational Linguistics Bangkok, Thailand conference publication tran-etal-2024-mol2lang 10.18653/v1/2024.langmol-1.12 https://aclanthology.org/2024.langmol-1.12/ 2024-08 97 102