# CrystalFormer-CSP: Thinking Fast and Slow for Crystal Structure Prediction

arXiv: https://arxiv.org/abs/2512.18251 · HTML: https://mlsanity.com/paper/2512.18251/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [RL's Razor: Why Online Reinforcement Learning Forgets Less](https://mlsanity.com/paper/2509.04259/) (2025)
- [Crystal Structure Prediction by Joint Equivariant Diffusion](https://mlsanity.com/paper/2309.04475/) (2023)
- [FlowMM: Generating Materials with Riemannian Flow Matching](https://mlsanity.com/paper/2406.04713/) (2024)
- [Space Group Informed Transformer for Crystalline Materials Generation](https://mlsanity.com/paper/2403.15734/) (2024)
- [Reinforcement Fine-Tuning for Materials Design](https://mlsanity.com/paper/2504.02367/) (2025)
- [Equivariant Diffusion for Crystal Structure Prediction](https://mlsanity.com/paper/2512.07289/) (2025)
- [AI-Driven Expansion and Application of the Alexandria Database](https://mlsanity.com/paper/2512.09169/) (2025)
- [Shotgun crystal structure prediction using machine-learned formation energies](https://mlsanity.com/paper/2305.02158/) (2023)
- [Self-Optimizing Machine Learning Potential Assisted Automated Workflow for Highly Efficient Complex Systems Material Design](https://mlsanity.com/paper/2505.08159/) (2025)
- [High-dimensional Optimization with Low Rank Tensor Sampling and Local Search](https://mlsanity.com/paper/2505.12383/) (2025)

## Built on by (most cited first, 1 of 1)

- [Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling](https://mlsanity.com/paper/2602.20210/) (2026)

## Abstract (arXiv)

Crystal structure prediction is a fundamental problem in materials science. We present CrystalFormer-CSP, an efficient framework that unifies data-driven heuristic and physics-driven optimization approaches to predict stable crystal structures for given chemical compositions. The approach combines pretrained generative models for space-group-informed structure generation and a universal machine learning force field for energy minimization. Reinforcement fine-tuning can be employed to further boost the accuracy of the framework. We demonstrate the effectiveness of CrystalFormer-CSP on benchmark problems and showcase its usage via web interface and language model integration.