用生成模型高效发现新分子与晶体结构，成本低且不依赖训练数据。
Generative structure search for efficient and diverse discovery of molecular and crystal structures
- 将扩散生成与随机搜索统一为基于能量场的采样过程。
- 相比传统方法，采样成本降低十倍以上，覆盖更多稳定结构。
- 适合探索训练数据之外的新化学组成，适合材料研发人员。
预测稳定和亚稳态结构是分子与材料发现的核心，但受限于高维能量景观搜索的高昂成本。深度生成模型虽能高效采样结构，但输出仍受训练数据影响，难以探索稀有但物理相关的能量极小值。我们提出生成式结构搜索（GSS），将基于扩散的生成与随机结构搜索（RSS）视为同一采样过程的两个极限情形，该过程由学习得到的梯度场与物理力共同驱动。结合数据先验加速采样，同时保留对局部极小值的能量引导探索。在分子与晶体系统中，GSS以超过十倍的采样效率实现更广泛的结构覆盖，且对训练分布外的成分依然有效。结果表明，GSS是一种具有物理基础的生成式搜索策略，可突破纯数据驱动采样的局限。
原文摘要 · Abstract (English)
Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimensional energy landscapes. Deep generative models offer efficient structure sampling, yet their outputs remain shaped by training data and can underexplore minima that are rare but physically relevant. We introduce generative structure search (GSS), a unified framework that formulates diffusion-based generation and random structure search (RSS) as limiting regimes of a common sampling process driven by learned score fields and physical forces. Coupling these drivers lets GSS use data priors to accelerate sampling while retaining energy-guided exploration of local minima. Across molecular and crystalline systems, GSS recovers diverse metastable structures with more than tenfold lower sampling cost than RSS for broad coverage and remains effective for compositions outside the training distribution. The results establish a physically grounded generative search strategy for discovering structures beyond the reach of data-driven sampling alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。