arXiv:2602. 17176v4 Announce Type: replace-cross Abstract: Crystal structure prediction (CSP), which aims to predict the 3D atomic arrangement of a crystal from its composition, is central to materials discovery and mechanistic understanding.
arXiv:2608. 07401v1 Announce Type: cross Abstract: The search for new crystalline materials spans an enormous compositional and structural space.
arXiv:2608. 13457v1 Announce Type: new Abstract: Generating crystals has recently attracted significant interest due to their broad applications in materials science.
The study benchmarks 12 deep generative crystal structure prediction models against the template-based TCSP 2.0 on 180 test structures, finding that template retrieval achieves the highest top‑1 success (68.3%). Most generative predictions overlap with template substitutions, and removing entire stoichiometric prototype families from training reduces accuracy by 50‑78%, indicating strong prototype dependence. Only a small subset of predictions remain after such removal, suggesting limited genuine de‑novo capability.
The paper introduces CG-OMatG, an equivariant Riemannian flow-based generative model that predicts molecular crystal structures using a coarse-grained, hierarchical representation. It treats molecules as rigid bodies, performs inter- and intra-molecular message passing, and learns to reconstruct molecule centroids, orientations, and lattice parameters conditioned on chemical species and conformer geometry. The model is trained on OMC25 and CSD datasets, fine-tuned with policy gradient reinforcement learning to favor low-energy structures, and validated against a CSP blind test benchmark using COMPACK packing-similarity analysis.
SymADiT is a symmetry‑aware variant of the All‑atom Diffusion Transformer (ADiT) designed for crystal generation. It uses Wyckoff‑based crystal representations and enforces symmetry constraints from the crystal’s space group and atom positions during latent‑space generative modeling. The approach yields stable, symmetric, and physically plausible crystals while maintaining competitive performance against both symmetry‑aware and symmetry‑agnostic models.
EP-Flow introduces a new framework for predicting disordered crystal structures without requiring site-level disorder annotations. It uses an Occupancy Distribution Matrix (ODM) to represent continuous site-by-species occupancies and enforces constraints through a transportation polytope. The method jointly generates occupancies, fractional coordinates, and lattice parameters, achieving state‑of‑the‑art performance on formula‑conditioned disordered CSP benchmarks and recovering chemically meaningful local disorder patterns.
arXiv:2608. 06448v1 Announce Type: cross Abstract: Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem.
Orbitol is a crystal generation model that uses Wyckoff-orbit tokens instead of atom tokens, enabling direct control over the space group of generated structures. It produces structures two to three orders of magnitude faster than symmetry‑aware baselines and achieves higher success rates in generating stable, novel structures that retain the requested symmetry. The authors also introduce SPARC, a score combining space‑group retention with distribution agreement, and demonstrate Orbitol’s effectiveness in generating high‑quality piezoelectric candidates with superior figures of merit.
arXiv:2609.01076v1 Announce Type: cross Abstract: Crystal generators can now propose periodic structures, but their control interfaces remain poorly matched to the mixed descriptors used in materials...
CrystalReasoner (CrysReas) is an end‑to‑end large language model framework that generates crystal structures from natural language instructions by incorporating physical priors as thinking tokens—such as crystallographic symmetry, local coordination, and predicted properties—before producing atomic coordinates. It then uses reinforcement learning with a multi‑objective reward to enforce physical validity, chemical consistency, and thermodynamic stability, and includes task‑specific rewards for property‑conditioned generation. Empirical results show that CrysReas outperforms prior methods, triples the S.U.N. ratio, and adapts reasoning length with increasing atom counts.
Generative models propose crystalline materials by learning composition and geometry, but unconditional sampling gives no direct control over the space group, which constrains whether responses such a...