arXiv Artificial Intelligence

uFlowCSP: Crystal Structure Prediction using Mean flow generative models

1 hour ago 11.09.2026 07:00 👁 2 views
uFlowCSP: Crystal Structure Prediction using Mean flow generative models

Quick summary

arXiv:2609.09799v1 Announce Type: cross Abstract: Crystal structure prediction (CSP) is fundamental to computational materials discovery. Generative models including CDVAE, DiffCSP, FlowMM, and CrystalFlow learn stable-crystal distributions directly, but diffusion and flow-matching inference requires tens to thousands of sequential network evaluations per candidate. We introduce uFlowCSP, a MeanFlow-based CSP model that learns the average, rather than instantaneous, probability-flow velocity. It generates a complete structure in one to five evaluations, delivering 5x-58x faster inference with

Key takeaways

  • arXiv:2609.09799v1 Announce Type: cross Abstract: Crystal structure prediction (CSP) is fundamental to computational materials discovery.
  • Generative models including CDVAE, DiffCSP, FlowMM, and CrystalFlow learn stable-crystal distributions directly, but diffusion and flow-matching inference requires tens to thousands of sequential network evaluations per candidate.
  • We introduce uFlowCSP, a MeanFlow-based CSP model that learns the average, rather than instantaneous, probability-flow velocity.

Why it matters

“uFlowCSP: Crystal Structure Prediction using Mean flow generative models” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗