发表机构
Imperial College London（帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GEODE首次在笛卡尔空间结合坐标与晶格扩散，通过Wyckoff约束保持对称性，实现11.9%的mSUN率，并引入模板过滤提升性能，支持对称与属性联合引导。
AI 中文摘要
大多数已知的无机晶体表现出对称的原子排列，然而生成模型往往无法重现这些对称性。迄今为止，显式强制这些对称性所产生的稳定且新颖的结构数量少于无约束生成。我们提出了生成等变轨道扩散引擎（GEODE），据我们所知，这是首个在笛卡尔空间中结合坐标和晶格扩散的模型。GEODE首先采样对称模板，然后联合生成晶格、原子坐标和原子类型，同时通过一种新颖的Wyckoff约束损失保持指定的对称性。笛卡尔扩散赋予坐标噪声一致的物理尺度，我们通过实验证明这能提升性能。无条件生成实现了11.9%的亚稳态、独特且新颖（mSUN）比率，而下一个最佳对称感知模型为7.7%。我们还引入了采样时间模板过滤，无需重新训练即可将mSUN提高约6%，使GEODE与领先的对称无关模型竞争。模板选择还支持联合对称性和属性引导，我们通过介电常数的无分类器引导进行了演示。
英文摘要
Most known inorganic crystals exhibit symmetric atomic arrangements, yet generative models often fail to reproduce them. Explicitly enforcing these symmetries has so far yielded fewer stable and novel structures than unconstrained generation. We introduce Generative Equivariant Orbit Diffusion Engine (GEODE), to our knowledge the first model to combine coordinate and lattice diffusion in Cartesian space. GEODE first samples symmetry templates, then jointly generates the lattice, atomic coordinates and atom types while preserving the specified symmetry with a novel Wyckoff-constrained loss. Cartesian diffusion gives coordinate noise a consistent physical scale that we empirically demonstrate improves performance. Unconditional generation achieves a metastable, unique and novel (mSUN) rate of 11.9%, compared with 7.7% for the next best symmetry-aware model. We also introduce sampling time template filtering, which increases mSUN by ~6% without retraining, making GEODE competitive with leading symmetry-agnostic models. Template selection also enables joint symmetry and property guidance, which we demonstrate through classifier-free guidance of permittivity.
Comments28 pages, 6 figures, 11 tables
