mlsanityData to 14 Oct 2026

Symmetry-Aware Bayesian Flow Networks for Crystal Generation

arXiv 2502.03146 ↗First posted 5 Feb 2025cs.LG cond-mat.mtrl-scicited by 9

Not on the map. Why?

Abstract (arXiv)

The discovery of new crystalline materials is essential to scientific and technological progress. However, traditional trial-and-error approaches are inefficient due to the vast search space. Recent advancements in machine learning have enabled generative models to predict new stable materials by incorporating structural symmetries and to condition the generation on desired properties. In this work, we introduce SymmBFN, a novel symmetry-aware Bayesian Flow Network (BFN) for crystalline material generation that accurately reproduces the distribution of space groups found in experimentally observed crystals. SymmBFN substantially improves efficiency, generating stable structures at least 50 times faster than the next-best method. Furthermore, we demonstrate its capability for property-conditioned generation, enabling the design of materials with tailored properties. Our findings establish BFNs as an effective tool for accelerating the discovery of crystalline materials.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 5 Feb 2025.

Builds on

16 of 45 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2021E(n) Equivariant Graph Neural Networkscited by 965
  4. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  5. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 148
  6. 2022Equivariance with Learned Canonicalization Functionscited by 109
  7. 2024FlowMM: Generating Materials with Riemannian Flow Matchingcited by 109
  8. 2023MatterGen: a generative model for inorganic materials designcited by 98
  9. 2024Fine-Tuned Language Models Generate Stable Inorganic Materials as Textcited by 93
  10. 2024Space Group Constrained Crystal Generationcited by 73
  11. 2023Bayesian Flow Networkscited by 63
  12. 2023Scalable Diffusion for Materials Generationcited by 54
4 more
  1. 2024FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributionscited by 53
  2. 2024Space Group Informed Transformer for Crystalline Materials Generationcited by 41
  3. 2021Normalizing flows for atomic solidscited by 39
  4. 2022Large-scale machine-learning-assisted exploration of the whole materials spacecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025Space Group Equivariant Crystal Diffusioncited by 15
  2. 2026Open Materials Generation with Inference-Time Reinforcement Learningcited by 8
  3. 2026DMFlow: Disordered Materials Generation by Flow Matchingcited by 5
  4. 2025MiAD: Mirage Atom Diffusion for De Novo Crystal Generationcited by 4
  5. 2025Generative Models for Crystalline Materialscited by 4
  6. 2026SLayerGen: a Crystal Generative Model for all Space and Layer Groupscited by 2
  7. 2025Unsupervised anomaly detection using Bayesian flow networks: application to brain FDG PET in the context of Alzheimer's diseasecited by 1
  8. 2026DynaCrys: Crystal Generation with Dynamic Space-Group Diffusioncited by 0
  9. 2026EP-Flow: Disordered Crystal Structure Prediction without Site-Level Annotationscited by 0