REVIEW 8 cited by
SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models
read the original abstract
Generating novel crystalline materials has the potential to lead to advancements in fields such as electronics, energy storage, and catalysis. The defining characteristic of crystals is their symmetry, which plays a central role in determining their physical properties. However, existing crystal generation methods either fail to generate materials that display the symmetries of real-world crystals, or simply replicate the symmetry information from examples in a database. To address this limitation, we propose SymmCD, a novel diffusion-based generative model that explicitly incorporates crystallographic symmetry into the generative process. We decompose crystals into two components and learn their joint distribution through diffusion: 1) the asymmetric unit, the smallest subset of the crystal which can generate the whole crystal through symmetry transformations, and; 2) the symmetry transformations needed to be applied to each atom in the asymmetric unit. We also use a novel and interpretable representation for these transformations, enabling generalization across different crystallographic symmetry groups. We showcase the competitive performance of SymmCD on a subset of the Materials Project, obtaining diverse and valid crystals with realistic symmetries and predicted properties.
Forward citations
Cited by 8 Pith papers
-
Planar Symmetric Pattern Generation
A new framework enforces planar group symmetries on 2D continuous functions without breaking continuity, with math formulation, approximation proofs, and validation on four design tasks.
-
Latent Diffusion Pretraining for Crystal Property Prediction
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
-
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S...
-
Conditional Generative Models Enable Targeted Exploration of MAX Phase Design Space
Conditional generative models double the rate of stable novel MAX phase structures by steering generation with MXene derivative counts and A-site binding energy surrogates, yielding five DFT-stable candidates out of t...
-
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
A unified multimodal flow model called MCFlow performs crystal structure prediction, de novo generation, and structure-conditioned atom type generation competitively with task-specific baselines on MP-20 and MPTS-52.
-
VASP Plugins: Linking the Vienna ab-initio Simulation Package with Python
A C++/pybind11 shared-memory plugin layer exposes VASP SCF and ionic data as NumPy arrays so Python can modify structure, forces, local potential, and occupancies in place.
-
Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist
HACO adapts MaskGIT from vision into MaskGXT with symmetry tokens and stratified sampling, reaching 79.06% METRe accuracy on MP-20 polymorph split versus 70.87% for the best baseline.
-
Composable Crystals: Controllable Materials Discovery via Concept Learning
VQ-VAE concept learning enables controllable recombination of crystal motifs to generate structures with reported gains in validity-stability-uniqueness-novelty metrics on MP-20 and Alex-MP-20.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.