Preprint · 2025 · Open access

A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER

Zihan Gai, Linyu Kuang

ChemRxiv · Published 29 October 2025 · DOI 10.26434/chemrxiv-2025-s9bqh

Open PDFView at the publisherCite this paper

In brief

“A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER” is a 2025 preprint by Zihan Gai and Linyu Kuang, published in ChemRxiv. OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at ChemRxiv.

Citations
1
Most cited in
2026 (1)
References
27
Authors
2

Abstract

The discovery of high-entropy layered double hydroxides (HE-LDHs) with optimal multi-vacancy configurations for enhanced oxygen evolution reaction (OER) catalysis is limited by the vast design space and high computational cost of traditional approaches. To overcome this, we propose LDH-VacGenie, a multimodal intelligent framework that combines deep learning, large language models, and Bayesian optimization for accelerated and interpretable design of HE-LDH electrocatalysts. LDH-VacGenie consists of four key modules: LDH-VacPredictor for performance prediction, SynthFlow-LLM for synthesis pathway generation, VacancyGen-Optimizer for efficient design exploration, and VacInterpret-Engine for explainable analysis of vacancy effects. Experiments show that LDH-VacGenie achieves high prediction accuracy, strong generalization, and significant acceleration in catalyst discovery. It identifies novel, synthesizable candidates with superior OER performance and provides atomic-level insights into vacancy–metal interactions. This framework establishes a new paradigm for rational and efficient design of advanced HE-LDH electrocatalysts.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Gai, Z., & Kuang, L. (2025). A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER. ChemRxiv. https://doi.org/10.26434/chemrxiv-2025-s9bqh

MLA 9

Gai, Zihan, and Linyu Kuang. “A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER.” ChemRxiv, 2025. https://doi.org/10.26434/chemrxiv-2025-s9bqh.

Chicago

Gai, Zihan and Linyu Kuang. 2025. “A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER.” ChemRxiv. https://doi.org/10.26434/chemrxiv-2025-s9bqh.

Harvard

Gai, Z. and Kuang, L. (2025) ‘A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER’, ChemRxiv. doi:10.26434/chemrxiv-2025-s9bqh.

IEEE

Z. Gai and L. Kuang, “A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER,” ChemRxiv, 2025, doi: 10.26434/chemrxiv-2025-s9bqh.

BibTeX

@misc{gai2025multimodal,
  title     = {{A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER}},
  author    = {Gai, Zihan and Kuang, Linyu},
  howpublished = {ChemRxiv},
  year      = {2025},
  doi       = {10.26434/chemrxiv-2025-s9bqh},
  url       = {https://doi.org/10.26434/chemrxiv-2025-s9bqh}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • oxygen evolution reaction
  • electrocatalyst discovery
  • large language models
  • Bayesian optimization
  • catalyst performance prediction

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Gai, Z., & Kuang, L. (2025). A Multimodal AI Framework for Accelerated Discovery and Explainable Design of Optimal Multi-Vacancy HE-LDHs for OER. ChemRxiv. https://doi.org/10.26434/chemrxiv-2025-s9bqh

How many times has this paper been cited?

1 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at ChemRxiv: sign in and open the PDF from this page.

Who wrote this paper?

Zihan Gai, Linyu Kuang.

What is the DOI of this paper?

10.26434/chemrxiv-2025-s9bqh, permanently at https://doi.org/10.26434/chemrxiv-2025-s9bqh. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.