🔥🔥🔥 A Summary on Generative AI for Material Discovery
A comprehensive survey on generative AI for material discovery. ✨
Table of Contents
| Title | Venue | Date | Code | Demo |
|---|---|---|---|---|
| ChatGPT in the Material Design: Selected Case Studies to Assess the Potential of ChatGPT |
Journal of Chemical Information and Modeling 2024 | 2024.01.18 | - | - |
 Crystal structure generation with autoregressive large language modeling |
Nature Communications 2024 | 2023.07.10 | Github | - |
|
Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
|ICLR 2024|2024.02.06|Github|-|
| 
Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering
|Arxiv 2024|2024.05.22|Github|-|
|
LLMatDesign: Autonomous Materials Discovery with Large Language Models
|Arxiv 2024|2024.06.19|Github|-|
| 
MatterGPT: A Generative Transformer for Multi-Property Inverse Design of Solid-State Materials
| Arxiv 2024 | 2024.08.14 | Github | - |
| GenMS: Generative Hierarchical Materials Search
| NeurIPS 2024 | 2024.09.10 | - | Demo |
| 
FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
| NeurIPS 2024 | 2024.10.30 | Github | - |
| 
Invariant Tokenization for Language Model Enabled Crystal Materials Generation
| NeurIPS 2024 | 2025.02.28 | Github | - |
| Title | Venue | Date | Code | Demo |
|---|---|---|---|---|
 Crystal Structure Prediction by Joint Equivariant Diffusion |
NeurIPS 2023 | 2023.07.30 | GitHub | - |
 MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design |
ICLR 2024 | 2023.10.16 | GitHub | - |
| UniMat: Scalable Diffusion for Materials Generation | Arxiv 2023 | 2023.10.18 | - | demo |
 MatterGen: A Generative Model for Inorganic Materials Design |
Nature 2025 | 2023.12.06 | GitHub | - |
 Space Group Constrained Crystal Generation |
ICLR 2024 | 2024.02.06 | GitHub | - |
 An Equivariant Flow Matching Framework for Learning Molecular Crystallization |
ICML 2024 Workshop | 2024.06.17 | GitHub | - |
 Multi-modal Conditioning for Metal-Organic Frameworks Generation Using 3D Modeling Techniques |
Nature Communications 2025 | 2024.07.05 | GitHub | - |
| FlowMM: Generating Materials with Riemannian Flow Matching |
ICML 2024 | 2024.07.07 | GitHub | - |
 Equivariant Diffusion for Crystal Structure Prediction |
ICML 2024 | 2024.07.21 | GitHub | - |
| GenMS: Generative Hierarchical Materials Search |
NeurIPS 2024 | 2024.09.10 | - | Demo |
| Title | Venue | Date | Code | Demo |
|---|---|---|---|---|
 Crystal Diffusion Variational Autoencoder for Periodic Material Generation |
ICLR 2022 | 2021.10.21 | GitHub | - |
 Deep learning generative model for crystal structure prediction |
NPJ computational materials 2024 | 2024.08.10 | GitHub | - |
| |Title|Venue|Date|Code|Demo|
|-|-|-|-|-|
| 
Periodic Graph Transformers for Crystal Material Property Prediction | NeurIPS 2022 | 2022.09.23 | GitHub | - |
| Resolving the data ambiguity for periodic crystals | NeurIPS 2022 | 2022.11.28 | - | - |
| Capturing long-range interaction with reciprocal space neural network | Arxiv 2022 | 2022.11.30 | - | - |
| A Crystal-Specific Pre-Training Framework for Crystal Material Property Prediction | Arxiv 2023 | 2023.06.08 | - | - |
|
Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction | ICML 2023 | 2023.06.12 | GitHub | - |
| 
From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction | ICLR 2024 | 2023.10.25| GitHub | - |
| Pretraining Strategies for Structure Agnostic Material Property Prediction | Journal of Chemical Information and Modeling 2024 | 2024.02.01 | - | - |
|
Complete and Efficient Graph Transformers for Crystal Material Property Prediction | ICLR 2024 | 2024.03.18 | GitHub | - |
| A Diffusion-Based Pre-training Framework for Crystal Property Prediction | AAAI 2024 | 2024.03.24 | - | - |
| Artificial Intelligence Driving Materials Discovery? Perspective on the Article: Scaling Deep Learning for Materials Discovery | Chemistry of Materials 2024 | 2024.08.08 | - | - |
For any questions, feedback, or collaboration regarding the integrated repository of papers and code, feel free to contact Liang Yan at yanliangfdu@gmail.com.