Skip to content

Similar papers

#graph neural networks Open access Aug 2026

CrystalGRW: generative modeling of crystal structures with targeted crystallographic properties via geodesic random walks

CrystalGRW is introduced, a diffusion-based generative model on Riemannian manifolds that proposes candidate crystal configurations in stable phases, validated through density functional theory calculations, thereby accelerating materials discovery and inverse design.

Krit Tangsongcharoen, T. Pakornchote, C. Atthapak et al. · 1 citation
#graph neural networks Open access Sep 2026

Pformer: a plug-and-play periodicity-aware embedding for crystal property prediction

Predicting macroscopic properties of crystalline materials from atomic structure remains a central challenge in computational materials science. We introduce Pformer, a modular crystal representation framework built around a Fourier-inspired source encoder. The source model is trained by supervised scalar-property regr...

Te-Shu Yao, Yun-Fei Zhao, Jiajun Bie et al. · 0 citations
Preprint Sep 2026

Transferable Graph Neural Network Surrogates for Molecular Dynamics Across Crystal Symmetries

We present a transferable graph neural network (GNN) surrogate framework for molecular dynamics (MD) that directly predicts atomic displacements and propagates atomistic configurations without explicit force evaluation or numerical time integration. The central objective of this work is to establish whether a common GN...

Judah Immanuel, A. Mahata, Aniruddha Maiti · 0 citations
Preprint Sep 2026

Symmetry-Aware Flow Matching for End-to-end Molecular Crystal Generation

SALA is introduced, a flow-matching model built on state--context separation that evolves only asymmetric-unit atomic coordinates and symmetry-compatible lattice parameters while predicting their updates from the full periodic environment, and enables end-to-end generation of complex, symmetry-constrained molecular cry...

Wen-Di Cai, Fan-Yang Mo · 1 citation
Book Open access Aug 2026

One Path to Model Them All: Learnable-Time Flow Matching for Crystal Structure and Energy Prediction

UniPath is proposed, a novel framework based on Learnable-Time Flow Matching that unifies crystal structure and energy prediction within a single probability path, and theoretically proves that under optimal velocity fields, these paths converge to a consistent trajectory.

Songyou Li, Mingze Li, Qianpu Liu et al. · 1 citation

Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction

Crystal structure governs material properties, making crystal structure prediction (CSP) a fundamental problem in materials science. Generative models are a promising approach for solving this problem, but the prevalence of polymorphism, coupled with large unit cells and complex packing geometry, makes the molecular CS...

Thomas Egg, H. W. Sullivan, Maya M. Martirossyan et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.