{
 "id": "duongttr/LPM-24-extend",
 "owner": "duongttr",
 "name": "LPM-24-extend",
 "downloads": 8,
 "likes": 2,
 "last_modified": "2025-02-04T05:35:13.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text2text-generation",
  "text-generation",
  "translation"
 ],
 "citation": "@inproceedings{tran-etal-2024-mol2lang,\n    title = \"{M}ol2{L}ang-{VLM}: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion\",\n    author = \"Tran, Duong  and\n      Pham, Nhat Truong  and\n      Nguyen, Nguyen  and\n      Manavalan, Balachandran\",\n    editor = \"Edwards, Carl  and\n      Wang, Qingyun  and\n      Li, Manling  and\n      Zhao, Lawrence  and\n      Hope, Tom  and\n      Ji, Heng\",\n    booktitle = \"Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)\",\n    month = aug,\n    year = \"2024\",\n    address = \"Bangkok, Thailand\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.langmol-1.12\",\n    doi = \"10.18653/v1/2024.langmol-1.12\",\n    pages = \"97--102\",\n    abstract = \"This paper introduces Mol2Lang-VLM, an enhanced method for refining generative pre-trained language models for molecule captioning using multimodal features to achieve more accurate caption generation. Our approach leverages the encoder and decoder blocks of the Transformer-based architecture by introducing third sub-layers into both. Specifically, we insert sub-layers in the encoder to fuse features from SELFIES strings and molecular images, while the decoder fuses features from SMILES strings and their corresponding descriptions. Moreover, cross multi-head attention is employed instead of common multi-head attention to enable the decoder to attend to the encoder{'}s output",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "fb84f5fea9787564b0bf8b75261a777724a6521f",
 "stated_evidence": "https://huggingface.co/datasets/duongttr/LPM-24-extend/blob/fb84f5fea9787564b0bf8b75261a777724a6521f/README.md",
 "file_evidence": "https://huggingface.co/datasets/duongttr/LPM-24-extend/tree/fb84f5fea9787564b0bf8b75261a777724a6521f",
 "card_nc": false
}