Automated Monitoring of Cultural Heritage Artifacts Using Semantic Segmentation

A new approach utilizing multi-head attention and the Inception v3 model has been developed for the automatic detection of cardiomegaly through X-ray images. This method integrates deep learning tools and attention mechanisms, enhancing the accuracy and efficiency of diagnosing cardiovascular diseases by leveraging a robust data collection phase and preprocessing techniques to improve image quality.

A new framework called Coupled Physics-Gated Adaptation (C-PGA) has been introduced to predict photochemical conversion in complex 3D-printed objects, utilizing a large dataset of optically printed specimens. This innovative approach addresses the limitations of conventional vision models in understanding the coupled interactions of optical and material physics that influence chemical states.

A novel deep learning framework for synthesizing healthy tissue in 3D brain MRI scans has been developed, achieving first place in the ASNR-MICCAI BraTS-Inpainting Challenge 2025. The method employs a U-Net architecture enhanced with random masking augmentation, yielding significant improvements in image quality metrics such as SSIM and PSNR.

HistoSpeckle-Net has been introduced as a novel deep learning architecture aimed at enhancing the reconstruction of complex medical images from multimode fiber (MMF) speckles, addressing limitations in existing data-intensive methods. This approach utilizes a distribution-aware learning strategy and a histogram-based mutual information loss to improve model robustness and reduce data reliance.

HVAdam, a novel full-dimension adaptive optimizer, has been introduced to address the performance gap between adaptive optimizers like Adam and non-adaptive methods such as SGD, particularly in training large-scale models. The new optimizer features continuously tunable adaptivity and a mechanism called incremental delay update (IDU) to enhance convergence across diverse optimization landscapes.

AraFinNews has been introduced as the largest publicly available Arabic financial news dataset, featuring 212,500 article-headline pairs from 2015 to 2025, aimed at enhancing Arabic financial text summarization using large language models (LLMs). The dataset serves as a benchmark for evaluating language understanding and generation in financial contexts, particularly through transformer-based models like mT5, AraT5, and FinAraT5.

A novel Physics-Informed Loss (PIL) function has been proposed to enhance the segmentation of cerebral arteries in digital subtraction angiography (DSA) sequences. This new approach addresses the limitations of traditional loss functions that often fail to account for the geometric and physical consistency of vascular boundaries, leading to improved accuracy in vessel predictions.

FedPromo introduces a federated learning framework that allows for the efficient adaptation of large-scale foundation models to new domains by optimizing lightweight proxy models on client devices, significantly reducing computational demands while preserving data privacy.