Xin Huang

Chest X-ray segmentation is a critical technique for the screening and diagnosis of common thoracic diseases such as pneumonia and COVID-19, providing essential support for clinical diagnosis and quantitative analysis. However, the inherent challenges of chest X-ray images, including blurry lesion boundaries and irregular contours, pose significant difficulties for accurate segmentation. To address this problem, we propose a Multi-Scale Deformable Attention Fusion Network (MSDAFNet) for lesion segmentation in chest X-rays. MSDAFNet adaptively perceives lesion regions of varying shapes and sizes, thereby enhancing the model's robustness to diverse pathological tissues. Specifically, we design a multi-scale deformable convolution attention module that employs channel grouping and dilated convolutions with different dilation rates to capture multi-scale feature maps without increasing parameters. Learnable offsets are introduced, allowing the convolution kernels to adaptively adjust sampling positions. Furthermore, considering the clustered distribution characteristics of small target lesion regions, a memory module is proposed before the decoder.This module establishes semantic correlations between image regions by introducing learnable key-value pairs and an attention mechanism, thereby supplementing convolutional features with the capability of modeling long-range dependencies.Extensive experiments conducted on two large-scale medical datasets, QaTa-COV19-v1 and QaTa-COV19-v2, demonstrate that MSDAFNet achieves higher accuracy and robustness in anatomical structure segmentation than existing methods, delivering competitive performance.

Accurate matching between molecular structures and NMR spectra is an important task in automated structure elucidation. However, existing methods still face difficulties in jointly modeling multi-scale molecular topology and effectively exploiting the complementary information provided by paired ¹H and ¹³C NMR spectra. To address these limitations, we propose SpecMol-MatchNet, a multimodal matching framework that integrates a hybrid molecular graph encoder, branch-specific spectral feature learning, and residual multimodal fusion. In the molecular branch, attention-based graph interaction is combined with multi-scale neighborhood aggregation to capture structural cues at different receptive fields. In the spectral branch, branch-specific attention enhancement and joint gating are introduced to better exploit the complementary characteristics of paired ¹H and ¹³C spectra. The resulting molecular and spectral representations are integrated through a residual fusion module for final matching prediction. Experimental results on benchmark datasets demonstrate that SpecMol-MatchNet achieves consistently better overall performance than representative baseline methods.

Efficient amide bond formation is pivotal in drug development, yet traditional methods often rely on pre‐activated substrates or toxic reagents. We present a copper‐catalyzed, CS ₂ ‐mediated direct amidation enabling carboxylic acids and anilines to couple under mild, aerobic conditions without pre‐activation. The strategy achieves late‐stage modification of pharmaceuticals, amino acids, and peptides, showcasing broad substrate tolerance and functional group compatibility. Mechanistic insights identify thiourea‐derived carbodiimide intermediates via oxygen‐dependent desulfurization.

Multi-round Q&A based on background text needs to infer the answer to the question through the current question, historical Q&A pairs, and background text. The pre-trained model has proved its effectiveness in this task; however, the existing model has many problems such as too many parameters and high resource consumption. We propose a knowledge transfer method that combines knowledge distillation, co-learning of similar datasets, and fine-tuning of similar tasks. Through multi-knowledge cooperative training from large model to small model, between different data sets, and between different tasks, the performance of the small model with low resource consumption can match or surpass that of the large model.