Pith. sign in

REVIEW 3 cited by

An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2005.07609 v3 pith:634BCBMK submitted 2020-05-15 physics.comp-ph cond-mat.mtrl-scics.LG

Zekun Ren , Siyu Isaac Parker Tian , Juhwan Noh , Felipe Oviedo , Guangzong Xing , Jiali Li , Qiaohao Liang , Ruiming Zhu
show 9 more authors
Armin G.Aberle Shijing Sun Xiaonan Wang Yi Liu Qianxiao Li Senthilnath Jayavelu Kedar Hippalgaonkar Yousung Jung Tonio Buonassisi
This is my paper · ORCID
classification physics.comp-phcond-mat.mtrl-scics.LG
keywords crystalsdesigngeneralinversecrystalframeworkgenerativeinvertible
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    MCFlow uses decoupled flow time axes for atom types and crystal structures so a single model handles crystal structure prediction, de novo generation, and atom-type generation.

  2. UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation

    cs.LG 2025-06 conditional novelty 5.0 of 10

    UniMate is a single model that generates metamaterial topology, predicts mechanical properties, and confirms density conditions, outperforming baselines on all three tasks.

  3. Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction

    cond-mat.mtrl-sci 2025-02 conditional novelty 5.0 of 10

    TransVAE-CSP replaces the encoder in the CDVAE crystal generator with an equivariant transformer and per-dataset radial basis functions, improving reconstruction and generation on three benchmark datasets.

Pith tools