Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling methods are ineffective at boldly exploring attractive regions of the materials space due to their maximum likelihood training. In this work, we offer an alternative CMD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. To that end, we introduce a domain-specific model, dubbed CliqueFlowmer, that incorporates recent advances of clique-based MBO into transformer and flow generation. We validate this model's optimization abilities and show that materials it produces strongly outperform those from generative baselines. To support specialized materials discovery applications and broader interdisciplinary research, we release our code, model weights, and additional project resources at https://github.com/znowu/CliqueFlowmer, https://colab.research.google.com/drive/1usUg7zezFkcYHlm2MdYwZUNJXf_YkWnY?usp=sharing, and https://x.com/kuba_AI/status/2033382617442345321.

翻译：深度学习的最新进展催生了基于神经网络的计算机材料发现（CMD）方法。该领域的众多问题涉及寻找能优化目标特性的材料。然而，日益流行的生成建模方法由于采用最大似然训练，在大胆探索材料空间的吸引区域方面效果不佳。在这项工作中，我们提出了一种基于离线模型优化（MBO）的替代CMD技术，该技术将目标材料特性的直接优化融合到生成过程中。为此，我们引入了一个领域专用模型，称为CliqueFlowmer，它将基于团的MBO的最新进展整合到Transformer和流生成中。我们验证了该模型的优化能力，并表明它生成的材料的性能远超基于生成的基线方法。为了支持专业材料发现应用及更广泛的跨学科研究，我们在https://github.com/znowu/CliqueFlowmer、https://colab.research.google.com/drive/1usUg7zezFkcYHlm2MdYwZUNJXf_YkWnY?usp=sharing和https://x.com/kuba_AI/status/2033382617442345321上发布了我们的代码、模型权重及其他项目资源。