D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation

Understanding and predicting the diverse conformational states of molecules is crucial for advancing fields such as chemistry, material science, and drug development. Despite significant progress in generative models, accurately generating complex and biologically or material-relevant molecular structures remains a major challenge. In this work, we introduce a diffusion model for three-dimensional (3D) molecule generation that combines a classifiable diffusion model, Diffusion Transformer, with multihead equivariant self-attention. This method addresses two key challenges: correctly attaching hydrogen atoms in generated molecules through learning representations of molecules after hydrogen atoms are removed; and overcoming the limitations of existing models that cannot generate molecules across multiple classes simultaneously. The experimental results demonstrate that our model not only achieves state-of-the-art performance across several key metrics but also exhibits robustness and versatility, making it highly suitable for early-stage large-scale generation processes in molecular design, followed by validation and further screening to obtain molecules with specific properties.

YOLO-MST: Multiscale deep learning method for infrared small target detection based on super-resolution and YOLO

With the advancement of aerospace technology and the increasing demands of military applications, the development of low false-alarm and high-precision infrared small target detection algorithms has emerged as a key focus of research globally. However, the traditional model-driven method is not robust enough when dealing with features such as noise, target size, and contrast. The existing deep-learning methods have limited ability to extract and fuse key features, and it is difficult to achieve high-precision detection in complex backgrounds and when target features are not obvious. To solve these problems, this paper proposes a deep-learning infrared small target detection method that combines image super-resolution technology with multi-scale observation. First, the input infrared images are preprocessed with super-resolution and multiple data enhancements are performed. Secondly, based on the YOLOv5 model, we proposed a new deep-learning network named YOLO-MST. This network includes replacing the SPPF module with the self-designed MSFA module in the backbone, optimizing the neck, and finally adding a multi-scale dynamic detection head to the prediction head. By dynamically fusing features from different scales, the detection head can better adapt to complex scenes. The mAP@0.5 detection rates of this method on two public datasets, SIRST and IRIS, reached 96.4% and 99.5% respectively, more effectively solving the problems of missed detection, false alarms, and low precision.

Discovery of 2D Materials via Symmetry-Constrained Diffusion Model

Generative model for 2D materials has shown significant promise in accelerating the material discovery process. The stability and performance of these materials are strongly influenced by their underlying symmetry. However, existing generative models for 2D materials often neglect symmetry constraints, which limits both the diversity and quality of the generated structures. Here, we introduce a symmetry-constrained diffusion model (SCDM) that integrates space group symmetry into the generative process. By incorporating Wyckoff positions, the model ensures adherence to symmetry principles, leading to the generation of 2,000 candidate structures. DFT calculations were conducted to evaluate the convex hull energies of these structures after structural relaxation. From the generated samples, 843 materials that met the energy stability criteria (Ehull < 0.6 eV/atom) were identified. Among these, six candidates were selected for further stability analysis, including phonon band structure evaluations and electronic properties investigations, all of which exhibited phonon spectrum stability. To benchmark the performance of SCDM, a symmetry-unconstrained diffusion model was also evaluated via crystal structure prediction model. The results highlight that incorporating symmetry constraints enhances the effectiveness of generated 2D materials, making a contribution to the discovery of 2D materials through generative modeling.

Machine learning topological energy braiding of non-Bloch bands

Machine learning has been used to identify phase transitions in a variety of physical systems. However, there is still a lack of relevant research on non-Bloch energy braiding in non-Hermitian systems. In this work, we study non-Bloch energy braiding in one-dimensional non-Hermitian systems using unsupervised and supervised methods. In unsupervised learning, we use diffusion maps to successfully identify non-Bloch energy braiding without any prior knowledge and combine it with k-means to cluster different topological elements into clusters, such as Unlink and Hopf link. In supervised learning, we train a Convolutional Neural Network (CNN) based on Bloch energy data to predict not only Bloch energy braiding but also non-Bloch energy braiding with an accuracy approaching 100%. By analysing the CNN, we can ascertain that the network has successfully acquired the ability to recognise the braiding topology of the energy bands. The present study demonstrates the considerable potential of machine learning in the identification of non-Hermitian topological phases and energy braiding.

Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model

Efficiently generating energetically stable crystal structures has long been a challenge in material design, primarily due to the immense arrangement of atoms in a crystal lattice. To facilitate the discovery of stable material, we present a framework for the generation of synthesizable materials, leveraging a point cloud representation to encode intricate structural information. At the heart of this framework lies the introduction of a diffusion model as its foundational pillar. To gauge the efficacy of our approach, we employ it to reconstruct input structures from our training datasets, rigorously validating its high reconstruction performance. Furthermore, we demonstrate the profound potential of Point Cloud-Based Crystal Diffusion (PCCD) by generating entirely new materials, emphasizing their synthesizability. Our research stands as a noteworthy contribution to the advancement of materials design and synthesis through the cutting-edge avenue of generative design instead of the conventional substitution or experience-based discovery.