PaperScope
LIVE · 2026-09-03 05:40 UTC

Text-guided flow matching enables sample-efficient crystal structure generation

Wentao Li

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.01076 v1
Submitted
2026-09-01

Abstract

Crystal generators can now propose periodic structures, but their control interfaces remain poorly matched to the mixed descriptors used in materials design. Text provides a compact way to combine composition, symmetry, prototype and property cues, yet it has not been clear whether such information can steer flow-based crystal generation. Here we introduce TFMat, a text-conditioned flow-matching framework that uses structured materials language as a semantic prior for a CrystalFlow generator. Across Perov-5, Carbon-24 and MP-20 crystal structure prediction benchmarks, TFMat improves one-candidate match rates over CrystalFlow and reaches a 92.04% MP-20 match rate with 20 candidates; in de novo generation, it improves element-count and density distribution alignment while retaining coarse property consistency in composition-selected outputs. These results position structured text as an inspectable control layer for translating human-readable materials intent into candidate crystals for downstream simulation and validation.

Comment: 20 pages

arXiv abs page · PDF · same-day batch