Multi Head Attention Enhanced Inception v3 for Cardiomegaly Detection

A recent study highlights the importance of automated crack detection in preserving cultural heritage artifacts through the use of semantic segmentation techniques. The research focuses on evaluating various U-Net architectures for pixel-level crack identification on statues and monuments, utilizing the OmniCrack30k dataset for quantitative assessments and real-world evaluations.

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 new framework named PETRG-3D has been proposed for automated 3D PET/CT report generation, addressing the growing need for efficient reporting in oncology due to a shortage of trained specialists. This model utilizes a dual-branch architecture to separately encode PET and CT volumes while incorporating style-adaptive prompts to standardize reporting across different hospitals.

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.

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.

The introduction of CommonVoice-SpeechRE marks a significant advancement in Speech Relation Extraction (SpeechRE) by providing a large-scale dataset of nearly 20,000 real human speech samples, addressing the limitations of existing synthetic datasets. This new benchmark aims to enhance the extraction of relation triplets directly from speech, which has been a challenge due to the lack of diversity in previous datasets.

DualGazeNet has been introduced as a biologically inspired dual-gaze query network aimed at enhancing salient object detection (SOD) while minimizing architectural complexity. This framework seeks to overcome challenges faced by existing SOD methods, which often suffer from feature redundancy and performance bottlenecks due to their intricate designs. By simplifying the architecture, DualGazeNet aims to achieve state-of-the-art accuracy and computational efficiency.