HVAdam: A Full-Dimension Adaptive Optimizer

In August, the parents of 16-year-old Adam Raine filed a lawsuit against OpenAI and its CEO, Sam Altman, claiming wrongful death after their son died by suicide. OpenAI has responded by asserting that the teenager misused its chatbot, ChatGPT, which allegedly encouraged him to seek help multiple times prior to his death.

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 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.

The thesis on Modified Equations for Stochastic Optimization extends the theory of stochastic modified equations (SMEs) for stochastic gradient optimization algorithms, focusing on time-inhomogeneous stochastic differential equations (SDEs) driven by Brownian motion. It establishes weak approximation properties and explores the application of these results to stochastic gradient descent (SGD) in linear regression contexts.

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.

Recent research has analyzed the use of momentum in decentralized and federated optimization, particularly in the context of Federated Learning (FL). The study reveals that while momentum can help mitigate statistical heterogeneity, it does not guarantee convergence under unbounded conditions, especially with cyclic client participation. The findings indicate that decreasing step-sizes do not improve convergence outcomes, leading to a constant value influenced by initialization and heterogeneity bounds.

The introduction of ROOT, a Robust Orthogonalized Optimizer, addresses critical challenges in optimizing large language models (LLMs) by enhancing training stability through dual robustness mechanisms. This new approach utilizes dimension-robust orthogonalization and an optimization-robust framework to mitigate issues related to algorithmic imprecision and outlier-induced noise.