Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

medical-9

Molecule Captioning

3260 papers • 126 benchmarks • 313 datasets

Molecular description generation entails the creation of a detailed textual depiction illuminating the structure, properties, biological activity, and applications of a molecule based on its molecular descriptors. It furnishes chemists and biologists with a swift conduit to essential molecular information, thus efficiently guiding their research and experiments.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in molecule-captioning-9

Trend

Dataset

Best Model

Actions

ChEBI-20

ChEBI-20

Libraries

i

Use these libraries to find molecule-captioning-9 models and implementations

Datasets

ChEBI-20

Subtasks

No subtasks available.

Most implemented papers

A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language

Anyi Rao, Ji-rong Wen, Yujie Zhou, Bing Su, Zhiwu Lu, Dazhao Du, Zhao-Qing Yang, Jiangmeng Li, Haoran Sun•Sun Sep 11 2022

A molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data via contrastive learning which enhances molecular property prediction and possesses capability to generate meaningful molecular graphs from natural language descriptions is proposed.

159

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

MolFM: A Multimodal Molecular Foundation Model

Zaiqing Nie, Yi Luo, Kai Yang, Massimo Hong, Xingyi Liu•Mon Jun 05 2023

This study introduces MolFM, a multimodal molecular foundation model designed to facilitate joint representation learning from molecular structures, biomedical texts, and knowledge graphs, and provides theoretical analysis that MolFM captures local and global molecular knowledge by minimizing the distance in the feature space between different modalities of the same molecule.

63 0

Unifying Molecular and Textual Representations via Multi-task Language Modelling

O. Winther, Jannis Born, Dimitrios Christofidellis, Giorgio Giannone, T. Laino, Matteo Manica•Sat Jan 28 2023

This work proposes the first multi-domain, multi-task language model that can solve a wide range of tasks in both the chemical and natural language domains and suggests that such models can robustly and efficiently accelerate discovery in physical sciences by superseding problem-specific fine-tuning and enhancing human-model interactions.

121 0

Translation between Molecules and Natural Language

Carl N. Edwards, Heng Ji, T. Lai, Kevin Ros, Garrett Honke•Sun Apr 24 2022

The results show that MolT5-based models are able to generate outputs, both molecules and captions, which in many cases are high quality, and consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation.

242 0

Empowering Molecule Discovery for Molecule-Caption Translation With Large Language Models: A ChatGPT Perspective

Jiliang Tang, Xiao Wei, Wenqi Fan, Hui Liu, Jiatong Li, Yunqing Liu, Qing Li•Sat Jun 10 2023

This work proposes a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning.

132 0

GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text

Peng Liu, Yiming Ren, Zhixiang Ren•Sun Aug 13 2023

GIT-Mol is introduced, a multi-modal large language model that integrates the Graph, Image, and Text information and proposes GIT-Former, a novel architecture that is capable of aligning all modalities into a unified latent space.

125 0

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery

Yuhan Chen, Nuwa Xi, Yanrui Du, Hao Wang, Jianyu Chen, Sendong Zhao, Bing Qin•Sun Sep 10 2023

This paper first introduces a retrieval-based prompting strategy to construct high-quality pseudo data, then explores the optimal method to effectively leverage this pseudo data to address the low-resource challenge by utilizing artificially-real data generated by Large Language Models (LLMs).

14 0

BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations

Jinhua Zhu, Lijun Wu, Qizhi Pei, Kaiyuan Gao, Rui Yan, Yingce Xia, Wei Zhang, Kehan Wu•Tue Oct 10 2023

A comprehensive pre-training framework that enriches cross-modal integration in biology with chemical knowledge and natural language associations, and distinguishes between structured and unstructured knowledge, leading to more effective utilization of information.

115 0

MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter

Yixin Cao, Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Kenji Kawaguchi, Xiang Wang, Tat-Seng Chua•Wed Oct 18 2023

MolCA retains the LM's ability of open-ended text generation and augments it with 2D graph information and extensively benchmarked it on tasks of molecule captioning, IUPAC name prediction, and molecule-text retrieval, on which MolCA significantly outperforms the baselines.

133 0

InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery

He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li•Sun Nov 26 2023

InstructMol, a multi-modal LLM, effectively aligns molecular structures with natural language via an instruction-tuning approach, utilizing a two-stage training strategy that adeptly combines limited domain-specific data with molecular and textual information.

95 0

Adding a benchmark result helps the community track progress.

Molecule Captioning | State-of-the-Art