← Back to all news
arXiv AI By Sourin Dey, Dipannoy Das Gupta, Lai Wei, Sadman Sadeed Omee, Jianjun Hu

uFlowCSP: Crystal Structure Prediction using Mean flow generative models

Read the original on arXiv AI →

uFlowCSP is a MeanFlow-based crystal structure prediction model that learns the average probability‑flow velocity, enabling it to generate complete crystal structures in one to five network evaluations. It achieves inference speeds 5×–58× faster than diffusion and flow‑matching methods while matching or surpassing their performance, with a chemistry‑ and symmetry‑aware Transformer that uses canonical atom ordering and per‑token chemistry embeddings. On the MP‑20 benchmark, uFlowCSP attains comparable or higher accuracy with far fewer evaluations and significantly lower wall‑clock time, demonstrating improved accuracy per network evaluation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 23

Deep Generative Crystal Structure Prediction: A Benchmark Study and a Controlled Test of Prototype Dependence

The study benchmarks 12 deep generative crystal structure prediction models against the template-based TCSP 2.0 on 180 test structures, finding that template retrieval achieves the highest top‑1 success (68.3%). Most generative predictions overlap with template substitutions, and removing entire stoichiometric prototype families from training reduces accuracy by 50‑78%, indicating strong prototype dependence. Only a small subset of predictions remain after such removal, suggesting limited genuine de‑novo capability.

By Lai Wei, Rongzhi Dong, Ying Feng, Madeline Miklos, Jianjun Hu
diffusionbenchmarks
More like this →
arXiv Machine Learning
6d ago

TCSP3.0: Template-Based Crystal Structure Prediction with Coefficient-Preserving Element Substitution and Structural Diversity

TCSP3.0 is an improved template‑based crystal structure prediction method that enforces coefficient‑preserving element mappings, substitutes species simultaneously on parsed structures, and validates each candidate’s composition and cell. It adds periodic‑number retrieval, soft oxidation‑state evidence, radius‑compatibility scoring, structural deduplication, and ORB‑v3 machine‑learning‑potential relaxation and energy ranking, achieving Top‑1 and Top‑20 match rates of 72.2 % and 90.6 % on the T180 benchmark and outperforming previous TCSP2.0 and several deep generative models. The method runs in a median of 28 s per target on two CPU cores, roughly ten times faster than CrystalFlow, with most gains attributed to the correctness fixes and structural deduplication.

By Ying Feng, Jeffrey Hu, Lai Wei, Liang Tao, Madeline Miklos, Dipannoy Das Gupta, Hossein Erfanshekooh, Jianjun Hu
ragbenchmarks
More like this →
arXiv AI
Sep 30

Where Should Physics Enter a Molecular Crystal Generator?

The paper introduces CrystAF, an all‑atom crystal flow‑map generation model, and evaluates where physics should be incorporated into generative crystal structure models. By applying physics‑informed post‑training, the authors improve molecular validity and crystal packing without altering sampling speed, while inference‑time corrections further refine the structures. The study demonstrates that post‑training and inference‑time physics are complementary, and that the post‑training approach transfers to other generators such as Clari‑M and MolCrystalFlow.

By Haocheng Tang, Junmei Wang, Wengong Jin
safety
More like this →
arXiv Machine Learning
Aug 28

Packora: Systematic Design for Generative Molecular Crystal Structure Prediction

Packora is a flow-based generative model designed for molecular crystal structure prediction (CSP). It jointly predicts atomic coordinates and lattice parameters from molecular graphs, supporting multi-component and organometallic crystals and allowing conditioning on conformers, stereochemistry, and space-group data. In evaluations inspired by the CCDC CSP blind test, Packora outperforms baselines on generation and ranking benchmarks, achieving superior matched-budget coverage, higher experimental-form recovery, lower ranks, and faster convergence.

By Nayoung Kim, Kiyoung Seong, Sungsoo Ahn
benchmarks
More like this →