# CrystalICL: Enabling In-Context Learning for Crystal Generation

arXiv: https://arxiv.org/abs/2508.20143 · HTML: https://mlsanity.com/paper/2508.20143/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [Crystal Structure Prediction by Joint Equivariant Diffusion](https://mlsanity.com/paper/2309.04475/) (2023)
- [Fine-Tuned Language Models Generate Stable Inorganic Materials as Text](https://mlsanity.com/paper/2402.04379/) (2024)
- [Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files](https://mlsanity.com/paper/2305.05708/) (2023)
- [Space Group Informed Transformer for Crystalline Materials Generation](https://mlsanity.com/paper/2403.15734/) (2024)
- [Are LLMs Ready for Real-World Materials Discovery?](https://mlsanity.com/paper/2402.05200/) (2024)
- [Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials](https://mlsanity.com/paper/2409.04481/) (2024)
- [MatExpert: Decomposing Materials Discovery by Mimicking Human Experts](https://mlsanity.com/paper/2410.21317/) (2024)
- [Periodic Materials Generation using Text-Guided Joint Diffusion Model](https://mlsanity.com/paper/2503.00522/) (2025)
- [Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers](https://mlsanity.com/paper/2406.09263/) (2024)

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

- [PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design](https://mlsanity.com/paper/2509.07150/) (2025)
- [L^2M^3OF: A Large Language Multimodal Model for Metal-Organic Frameworks](https://mlsanity.com/paper/2510.20976/) (2025)

## Abstract (arXiv)

Designing crystal materials with desired physicochemical properties remains a fundamental challenge in materials science. While large language models (LLMs) have demonstrated strong in-context learning (ICL) capabilities, existing LLM-based crystal generation approaches are limited to zero-shot scenarios and are unable to benefit from few-shot scenarios. In contrast, human experts typically design new materials by modifying relevant known structures which aligns closely with the few-shot ICL paradigm. Motivated by this, we propose CrystalICL, a novel model designed for few-shot crystal generation. Specifically, we introduce a space-group based crystal tokenization method, which effectively reduces the complexity of modeling crystal symmetry in LLMs. We further introduce a condition-structure aware hybrid instruction tuning framework and a multi-task instruction tuning strategy, enabling the model to better exploit ICL by capturing structure-property relationships from limited data. Extensive experiments on four crystal generation benchmarks demonstrate the superiority of CrystalICL over the leading baseline methods on conditional and unconditional generation tasks.