We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Instead of intricate, multi-stream designs, CrystalDiT employs a unified transformer that imposes a powerful inductive bias: treating lattice and atomic properties as a single, interdependent system. Combined with a periodic table-based atomic representation and a balanced training strategy, our approach achieves 9.62% SUN (Stable, Unique, Novel) rate on MP-20, substantially outperforming recent methods including FlowMM (4.38%) and MatterGen (3.42%). Notably, CrystalDiT generates 63.28% unique and novel structures while maintaining comparable stability rates, demonstrating that architectural simplicity can be more effective than complexity for materials discovery. Our results suggest that in data-limited scientific domains, carefully designed simple architectures outperform sophisticated alternatives that are prone to overfitting..

Current leading methods for molecular conformation generation often rely on computationally intensive diffusion models in 3D space, which struggle with accurately modeling conformational manifolds and rigorously maintaining SE(3) equivariance. These limitations hinder both performance and efficiency, and can complicate integration with standard tools like RDKit. To overcome these challenges, we introduce CoFM, a novel generative framework that pioneers the concept of an autoencoder-induced, fully SE(3)-invariant latent space. This approach decouples SE(3) equivariance constraints from the generation process, enabling seamless integration of RDKit’s physicochemical priors. Furthermore, CoFM is the first to integrate latent flow matching within this invariant geometric subspace, significantly enhancing generation efficacy with fewer iterative steps. Experimental validation demonstrates that our method generates high-quality results with fewer iterations, achieving significant improvements in key Precision metrics and ensuring greater energy authenticity.

In the field of structural biology, Cryo-EM based high-resolution 3-D structure reconstruction of complex macromolecules is a vital step. Although multiple attempts have been tried within this framework to consider quality-degrading factors such as imaging noise, non-uniform distribution of particle orientations, and sample heterogeneity in order to achieve high resolution, there is still a substantial gap between the best reconstruction resolution achieved by the existing methods and the hard resolution provided by the imaging device. Here, we introduce CryoGS, a novel 3-D reconstruction method for Cryo-EM structures using Gaussian splatting. Through the integration of 3-D Gaussian representations into neural network learning, CryoGS employs a spatial domain approach to optimize learnable 3-D Gaussians and project them into 2-D images using the splatting technique. Compared with the existing methods, CryoGS achieves significant improvements in resolution, isotropy, and computational efficiency. For example, CryoGS achieves a resolution of 2.217 $\AA$ on EMPIAR-10492 dataset, approaching its theoretical limit of 2.2 $\AA$, while the best resolution achieved by the existing methods is 3.805 $\AA$. Furthermore, CryoGS exhibits remarkable robustness in reconstructing heterogeneous structures and high-resolution models under extreme conditions such as pose inaccuracy, limited particle data, and high noise. Based on these results, we believe that CryoGS has great potential to be a powerful tool for Cryo-EM applications to ensure enhanced resolution, robustness, and efficiency.

The ground-state conformation of a molecule is often decisive for its properties. However, experimental or computational methods, such as density functional theory (DFT), are time-consuming and labor-intensive for obtaining this conformation. Deep learning (DL) based molecular representation learning (MRL) has made significant advancements in molecular modeling and has achieved remarkable results in various tasks. Consequently, it has emerged as a promising approach for directly predicting the ground-state conformation of molecules. In this regard, we introduce GTMGC, a novel network based on Graph-Transformer (GT) that seamlessly predicts the spatial configuration of molecules in a 3D space from their 2D topological architecture in an end-to-end manner. Moreover, we propose a novel self-attention mechanism called Molecule Structural Residual Self-Attention (MSRSA) for molecular structure modeling. This mechanism not only guarantees high model performance and easy implementation but also lends itself well to other molecular modeling tasks. Our method has been evaluated on the Molecule3D benchmark dataset and the QM9 dataset. Experimental results demonstrate that our approach achieves remarkable performance and outperforms current state-of-the-art methods as well as the widely used open-source software RDkit.