ChemMLLM：面向分子理解与生成的化学多模态大语言模型

Computer Science > Machine Learning arXiv:2505.16326 (cs) [Submitted on 22 May 2025 (v1), last revised 25 Sep 2026 (this version, v3)] Title:ChemMLLM: Chemical Multimodal Large Language Model Authors:Qian Tan, Di Zhang, Ben Gao, Peng Xia, Wanhao Liu, Shufei Zhang, Wanli Ouyang, Lei Bai, Yuqiang Li, Tianfan Fu View a PDF of the paper titled ChemMLLM: Chemical Multimodal Large Language Model, by Qian Tan and 9 other authors View PDF HTML (experimental) Abstract:Recent years have seen rapid progress in multimodal large language models (MLLMs) in the field of chemistry. However, chemical MLLMs that can handle cross-modal understanding and generation remain underexplored. To fill this gap, we propose ChemMLLM, a unified chemical multimodal large language model for molecule understanding and generation. In this work, we design five types of multimodal tasks across text, molecular SMILES strings and images, and curate the datasets. We benchmark ChemMLLM against a range of general leading MLLMs, Chemical LLMs and specialized models on these tasks. Experimental results show that ChemMLLM achieves superior performance among general-purpose MLLMs and close performance to specialized models across all evaluated tasks. Our work extends the capabilities of chemical multimodal large language models to the realm of image generation, demonstrating the feasibility of unifying multiple cross-modal chemical tasks within a single foundation model and enabling more intuitive, visual human-AI interaction. Comments: Subjects: Machine Learning (cs.LG) Cite as: arXiv:2505.16326 [cs.LG] (or arXiv:2505.16326v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2505.16326 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Qian Tan [view email] [v1] Thu, 22 May 2025 07:32:17 UTC (2,077 KB) [v2] Mon, 4 Aug 2025 06:14:13 UTC (1,951 KB) [v3] Fri, 25 Sep 2026 17:42:44 UTC (2,971 KB) Full-text links: Access Paper: View a PDF of the paper titled ChemMLLM: Chemical Multimodal Large Language Model, by Qian Tan and 9 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2025-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)