# L^2M^3OF: A Large Language Multimodal Model for Metal-Organic Frameworks

arXiv: https://arxiv.org/abs/2510.20976 · HTML: https://mlsanity.com/paper/2510.20976/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 14 of 14)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Probing the limitations of multimodal language models for chemistry and materials research](https://mlsanity.com/paper/2411.16955/) (2024)
- [Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints](https://mlsanity.com/paper/2203.14352/) (2022)
- [Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks](https://mlsanity.com/paper/2212.03447/) (2022)
- [Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation](https://mlsanity.com/paper/2503.00152/) (2025)
- [Less can be more for predicting properties with large language models](https://mlsanity.com/paper/2406.17295/) (2024)
- [MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models](https://mlsanity.com/paper/2506.00198/) (2025)
- [The Rise of Generative AI for Metal-Organic Framework Design and Synthesis](https://mlsanity.com/paper/2508.13197/) (2025)
- [deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models](https://mlsanity.com/paper/2502.02189/) (2025)
- [CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning](https://mlsanity.com/paper/2506.17345/) (2025)
- [CrystalICL: Enabling In-Context Learning for Crystal Generation](https://mlsanity.com/paper/2508.20143/) (2025)
- [A Python library for efficient computation of molecular fingerprints](https://mlsanity.com/paper/2403.19718/) (2024)

## Built on by (most cited first, 2 of 2)

- [OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields](https://mlsanity.com/paper/2605.29833/) (2026)
- [Atomistic Language Models Understand and Generate Materials](https://mlsanity.com/paper/2606.21395/) (2026)

## Abstract (arXiv)

Large language models have demonstrated remarkable reasoning capabilities across diverse natural language tasks. However, comparable breakthroughs in scientific discovery are more limited, because understanding complex physical phenomena demands multifaceted representations far beyond language alone. A compelling example is the design of functional materials such as MOFs-critical for a range of impactful applications like carbon capture and hydrogen storage. Navigating their vast and intricate design space in language-based representations interpretable by LLMs is challenging due to the numerous possible three-dimensional atomic arrangements and strict reticular rules of coordination geometry and topology. Despite promising early results in LLM-assisted discovery for simpler materials systems, MOF design remains heavily reliant on tacit human expertise rarely codified in textual information alone. To overcome this barrier, we introduce L2M3OF, the first multimodal LLM for MOFs. L2M3OF integrates crystal representation learning with language understanding to process structural, textual, and knowledge modalities jointly. L2M3OF employs a pre-trained crystal encoder with a lightweight projection layer to compress structural information into a token space, enabling efficient alignment with language instructions. To facilitate training and evaluation, we curate a structure-property-knowledge database of crystalline materials and benchmark L2M3OF against state-of-the-art closed-source LLMs such as GPT-5, Gemini-2.5-Pro and DeepSeek-R1. Experiments show that L2M3OF outperforms leading text-based closed-source LLMs in property prediction and knowledge generation tasks, despite using far fewer parameters. These results highlight the importance of multimodal approaches for porous material understanding and establish L2M3OF as a foundation for next-generation AI systems in materials discovery.