# Design Topological Materials by Reinforcement Fine-Tuned Generative Model

arXiv: https://arxiv.org/abs/2504.13048 · HTML: https://mlsanity.com/paper/2504.13048/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 96 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules](https://mlsanity.com/paper/1906.00957/) (2019)
- [Inverse design of 3d molecular structures with conditional generative neural networks](https://mlsanity.com/paper/2109.04824/) (2021)
- [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024)
- [Space Group Constrained Crystal Generation](https://mlsanity.com/paper/2402.03992/) (2024)
- [An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties](https://mlsanity.com/paper/2005.07609/) (2020)
- [LLMatDesign: Autonomous Materials Discovery with Large Language Models](https://mlsanity.com/paper/2406.13163/) (2024)
- [Space Group Informed Transformer for Crystalline Materials Generation](https://mlsanity.com/paper/2403.15734/) (2024)
- [Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints](https://mlsanity.com/paper/2203.14352/) (2022)
- [Crystalline Material Discovery in the Era of Artificial Intelligence](https://mlsanity.com/paper/2408.08044/) (2024)
- [Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials](https://mlsanity.com/paper/2202.05255/) (2022)
- [Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers](https://mlsanity.com/paper/2406.09263/) (2024)
- [InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors](https://mlsanity.com/paper/2409.08065/) (2024)
- [Predicting Many Crystal Properties via an Adaptive Transformer-based Framework](https://mlsanity.com/paper/2405.18944/) (2024)

## Abstract (arXiv)

Topological insulators (TIs) and topological crystalline insulators (TCIs) are materials with unconventional electronic properties, making their discovery highly valuable for practical applications. However, such materials, particularly those with a full band gap, remain scarce. Given the limitations of traditional approaches that scan known materials for candidates, we focus on the generation of new topological materials through a generative model. Specifically, we apply reinforcement fine-tuning (ReFT) to a pre-trained generative model, thereby aligning the model's objectives with our material design goals. We demonstrate that ReFT is effective in enhancing the model's ability to generate TIs and TCIs, with minimal compromise on the stability of the generated materials. Using the fine-tuned model, we successfully identify a large number of new topological materials, with Ge2Bi2O6 serving as a representative example--a TI with a full band gap of 0.26 eV, ranking among the largest known in this category.