DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion

📅 2026-08-07
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenge of efficiently generating novel crystalline materials that satisfy crystallographic symmetry, elemental composition, and geometric continuity constraints within a vast compositional and structural space. It proposes a coupled symbolic diffusion framework that dynamically evolves space groups, Wyckoff positions, and elemental assignments, guided by crystallographic group–subgroup relationships to enable structured space-group transitions. A pretrained symmetry codebook is introduced to jointly constrain both the decoder and the geometric model. This approach achieves, for the first time, joint generation of space groups and crystal structures, demonstrating state-of-the-art performance across two independent relaxation evaluation engines. It enables efficient generation of highly stable, novel, and unique crystals, excelling particularly in preserving nontrivial post-relaxation symmetries, while supporting rapid sampling.
📝 Abstract
The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires jointly modeling discrete crystallographic symmetry, elemental composition, and continuous geometry. We introduce DynaCrys, a generative model for crystals in which the space group co-evolves with Wyckoff occupations and elements through a coupled symbolic diffusion process. The structured space-group transitions follow crystallographic group-subgroup relations. As the space group changes, a shared, pretrained symmetry codebook provides both the legality-constrained stochastic decoder and the symmetry-constrained crystal-geometry model with a common representation of the corresponding Wyckoff vocabulary. Across large-scale evaluations using two independent relaxation-and-evaluation engines, DynaCrys achieves best-in-class performance in symmetry-aware discovery of stable, unique, and novel crystals, both overall and under the additional requirement of nontrivial post-relaxation symmetry. It also enables fast sampling while generating structures with consistently low relaxation-induced structural displacements.
Problem

Research questions and friction points this paper is trying to address.

crystal generation
space-group diffusion
Wyckoff positions
symmetry-aware discovery
crystallographic symmetry
Innovation

Methods, ideas, or system contributions that make the work stand out.

dynamic space-group diffusion
symmetry-aware crystal generation
Wyckoff occupation
symbolic diffusion
crystallographic group-subgroup relations
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Z
Zhuotao Jin
NVIDIA; Center for Computational Science and Engineering, Massachusetts Institute of Technology; Department of Materials Science and Engineering, Massachusetts Institute of Technology; John A. Paulson School of Engineering and Applied Sciences, Harvard University
X
Xiaoyun Wang
NVIDIA
N
Nicholas Brawand
The MITRE Corporation
Roman Zubatyuk
Roman Zubatyuk
NVIDIA
MLIPcomputational chemistrydata science
Atul Thakur
Atul Thakur
Associate Professor of Mechanical Engineering, Indian Institute of Technology Patna
Physics-aware planning for roboticsvirtual and augmented realityrobotics simulation involving fluid-rigid body interactions
Eric Qu
Eric Qu
PhD Student, UC Berkeley
Geometric Deep LearningAI for ScienceSequence Modeling
Boris Kozinsky
Boris Kozinsky
Harvard University, Bosch Research
Computational materials sciencebatteriesthermoelectricscatalysismachine learning
J
Justin Smith
NVIDIA