Siamese Foundation Models for Crystal Structure Prediction

[2503.10471] Siamese Foundation Models for Crystal Structure Prediction Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Condensed Matter > Materials Science arXiv:2503.10471 (cond-mat) [Submitted on 13 Mar 2025 ( v1 ), last revised 14 Apr 2026 (this version, v2)] Title: Siamese Foundation Models for Crystal Structure Prediction Authors: Liming Wu , Wenbing Huang , Rui Jiao , Jianxing Huang , Liwei Liu , Yipeng Zhou , Hao Sun , Yang Liu , Fuchun Sun , Yuxiang Ren , Jirong Wen View a PDF of the paper titled Siamese Foundation Models for Crystal Structure Prediction, by Liming Wu and 10 other authors View PDF HTML (experimental) Abstract: Predicting crystal structures from chemical compositions is a fundamental challenge in materials discovery, complicated by complex 3D geometries that distinguish it from fields like protein folding. Here, we present Diffusion-based Crystal Omni (DAO), a pretrain-finetune framework for crystal structure prediction integrating two Siamese foundation models: a structure generator and an energy predictor. The generator is pretrained via a two-stage pipeline on a vast dataset of stable and unstable structures, leveraging the predictor to relax unstable configurations and guide the generative sampling. Across two well-known benchmarks, pretraining significantly enhances performance across multiple backbone architectures. Ablation studies confirm that the synergy between the generator and predictor mutually benefits both components. We further validate DAO on three real-world superconductors ($\text{Cr}_6\text{Os}_2$, $\text{Zr}_{16}\text{Rh}_8\text{O}_4$, and $\text{Zr}_{16}\text{Pd}_8\text{O}_4$) typically inaccessible to conventional computation. For $\text{Cr}_6\text{Os}_2$, DAO achieves a 100\% match rate with experimental references and an atomic-position error of 0.0012 under 20-shot generation, performing over 2000$\times$ faster per iteration than DFT-based structure predictors. These compelling results collectively highlight the potential of our approach for advancing materials science research. Subjects: Materials Science (cond-mat.mtrl-sci) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2503.10471 [cond-mat.mtrl-sci] (or arXiv:2503.10471v2 [cond-mat.mtrl-sci] for this version) https://doi.org/10.48550/arXiv.2503.10471 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Liming Wu [ view email ] [v1] Thu, 13 Mar 2025 15:44:16 UTC (3,520 KB) [v2] Tue, 14 Apr 2026 03:47:25 UTC (3,649 KB) Full-text links: Access Paper: View a PDF of the paper titled Siamese Foundation Models for Crystal Structure Prediction, by Liming Wu and 10 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cond-mat.mtrl-sci < prev | next > new | recent | 2025-03 Change to browse by: cond-mat cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Chemical-space completeness through iterative crystal-structure generation and model adaptation#1117277
• CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy#818729
• CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy#808737
• Multi-scale structural dataset of a crystalline reservoir analogue (Northern Odenwald)#207650
• Multiscale Interpretable Deep-Learning Framework for the Identification and Visualization of Deformation Stages in Molecular Dynamics Trajectory#1015798