论文

GaDiT:面向无序原子结构的图扩散 Transformer 生成与逆向设计模型

Graph diffusion transformer for interpretable generation and inverse design of disordered atomic structures

精选理由

arXiv 上的新材料生成模型论文:GaDiT 用动态周期图加扩散 Transformer 生成非晶碳、非晶硅等无序结构,采样比 corrector 方法快约百倍,还支持按性质条件逆向设计并给出可解释的原子归因分析。做材料模拟或生成模型的人可以看看。

论文提出 Graph Amorphous Diffusion Transformer(GaDiT),一种结合动态周期图、掩码条件机制和区间加权训练噪声分布的生成模型,用于无序原子结构的生成与逆向设计。

正文

采样速度相比现有基于 corrector 的方法加速两个数量级,并在二维非晶碳、三维非晶硅和非晶二氧化硅上完成验证。GaDiT 支持在统一模型内以单一或组合的结构特征、物理性质和制备条件作为条件进行生成,并能进行超出训练分布的结构-性质范围逆向设计。

作者还提出条件原子响应映射分析,用于解读结构及训练网络,识别决定目标性质的全局结构描述符和局部原子环境。该工作为无序材料的可解释生成与性质发现提供了通用框架,适合材料计算与生成模型方向的研究者关注。

原文 · arXiv cs.LG

Graph diffusion transformer for interpretable generation and inverse design of disordered atomic structures

Atomic disorder offers a potent degree of freedom to tailor material properties, yet the resulting vast configuration space obscures structure-property relations and hinders rational inverse design. Here we introduce Graph Amorphous Diffusion Transformer (GaDiT), a generative model that combines dynamic periodic graphs, masked conditioning and an interval-weighted training-noise distribution. GaDiT generates high-quality disordered structures while accelerating sampling by two orders of magnitude compared with existing corrector-based approaches, as demonstrated across two-dimensional amorphous carbon and three-dimensional amorphous silicon and silica. Moreover, GaDiT supports conditional generation under single or combined structural features, physical properties and preparation conditions in a unified model, and enables inverse design that expands accessible structure-property ranges beyond the training distribution. To interpret these structures and the trained network, we propose a conditioned atomic response mapping analysis, revealing both the global structural descriptors and the local atomic environments that govern target properties. Overall, GaDiT establishes a general framework for interpretable generation, inverse design and structure-property discovery for disordered atomic structures.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:GaDiT、扩散模型、材料生成、逆向设计,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Jiani Hu, Chenyan Wang, Yongkun Yang, Guanyu Hou, Jihaochen Zhang, Lei Liu, Ji Chen),经 AITOP 多维评分管线结构化提炼。