mlsanityData to 14 Oct 2026

CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials

arXiv 2605.17254 ↗First posted 17 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target properties from given structures, whereas the latter generates candidate structures according to desired properties. Although the decoupled paradigm facilitates the implementation of a ``generation--evaluation--screening'' workflow, the inconsistency between the generative model and the property prediction model in terms of representation spaces and training objectives can readily introduce data distribution shifts and evaluator bias, thereby limiting the stability of closed-loop optimization. In this work, we propose CatalyticMLLM, a unified graph--text multimodal large language model for catalytic materials, which integrates property prediction and inverse design within the same model and shared representation space. Under this unified framework, CatalyticMLLM can not only perform reliable property prediction by leveraging three-dimensional structures and textual information, but also generate and screen physically feasible CIF candidates conditioned on target properties, thereby forming a closed-loop optimization workflow of ``inverse design--prediction--screening--redesign.'' Experimental results demonstrate that this unified paradigm outperforms decoupled baselines on both catalytic relaxed-energy prediction and inverse design tasks, validating the effectiveness of jointly modeling property prediction and structure generation within a single multimodal model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 17 May 2026.

Builds on

23 of 38 references.

References · 23

  1. 2021E(n) Equivariant Graph Neural Networkscited by 965
  2. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  3. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  4. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  5. 2020Directional Message Passing for Molecular Graphscited by 561
  6. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  7. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  8. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  9. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  10. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  11. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 256
  12. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
11 more
  1. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  2. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 204
  3. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 148
  4. 2024Fine-Tuned Language Models Generate Stable Inorganic Materials as Textcited by 93
  5. 2021MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extractioncited by 83
  6. 2024Space Group Constrained Crystal Generationcited by 73
  7. 2023Scalable Diffusion for Materials Generationcited by 54
  8. 2022Spherical Channels for Modeling Atomic Interactionscited by 47
  9. 2024Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planningcited by 29
  10. 2024Multimodal Language and Graph Learning of Adsorption Configuration in Catalysiscited by 15
  11. 2025QE-Catalytic: A Graph-Language Multimodal Base Model for Relaxed-Energy Prediction in Catalytic Adsorptioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation
  2. 2024Leveraging Chemistry Foundation Models to Facilitate Structure Focused Retrieval Augmented Generation in Multi-Agent Workflows for Catalyst and Materials Design
  3. 2026Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
  4. 2026Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model Framework
  5. 2025Large language models in materials science and the need for open-source approaches
  6. 2026Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents
  7. 2026Catalyst Diffusion Transformer: Generative Inverse Design of Heterogeneous Catalysts
  8. 2024Foundational Large Language Models for Materials Research