New prosthetic arms combine artificial intelligence, machine learning and advanced sensor systems. If you've ever wondered what's next for prosthetic technology, you're not alone. For many people living with limb loss, finding a prosthetic that feels natural and works seamlessly with their body has always been a challenge. Now, a California startup called Atom Bodies is making headlines for its groundbreaking approach to prosthetic technology. By combining artificial intelligence, machine learning and advanced sensor systems, Atom Bodies is developing mind-controlled robotic arms that could soon make highly advanced prosthetics accessible to thousands of amputees.

From his vantage point behind the sweeping arc of glass windows at Amsterdam's city hall, Paul de Koning, a consultant to the city whose résumé includes stops at various agencies in the Dutch welfare state, had viewed the same system with pride. De Koning, who managed Smart Check's pilot phase, was excited about what he saw as the project's potential to improve efficiency and remove bias from Amsterdam's social benefits system. A team of fraud investigators and data scientists had spent years working on Smart Check, and de Koning believed that promising early results had vindicated their approach. The city had consulted experts, run bias tests, implemented technical safeguards, and solicited feedback from the people who'd be affected by the program--more or less following every recommendation in the ethical-AI playbook. "I got a good feeling," he told us.

During an address at Fort Bragg on Tuesday, President Trump announced that several Army base titles would be restored to their original names after changes made during the Biden administration. The U.S. Army is giving its soldiers a high-tech edge in the fight against drones, and it's called SMASH. During a live-fire training exercise on June 6 in Germany, a soldier with the 3rd Squadron, 2nd Cavalry Regiment used the SMASH 2000L smart scope mounted on an M4A1 rifle to target drones in the sky. The demo was part of Project Flytrap, a multinational training event. U.S. Soldiers assigned to 3rd Squadron, 2nd Cavalry Regiment set up the Wingman and Pitbull portable counter-unmanned aerial system devices during Project Flytrap at Joint Multinational Readiness Center, Hohenfels Training Area, Hohenfels, Germany, June 7, 2025.

Russia launched a large-scale drone-and-missile assault on Ukraine, killing one person in Kyiv and two in the southern port city of Odesa. At least 13 people were injured. A Ukrainian drone attack on a petrol station in the Russian city of Belgorod killed one person and injured four others, the region's governor, Vyacheslav Gladkov, said. Ukrainian President Volodymyr Zelenskyy said Russia's attack on Kyiv was "one of the biggest" in the three-year-old war. It caused several fires and damaged buildings, including St Sophia Cathedral, a UNESCO World Heritage landmark.

We consider the problem of propagating the uncertainty from a possibly large number of random inputs through a computationally expensive model. Stratified sampling is a well-known variance reduction strategy, but its application, thus far, has focused on models with a limited number of inputs due to the challenges of creating uniform partitions in high dimensions. To overcome these challenges, we perform stratification with respect to the uniform distribution defined over the unit interval, and then derive the corresponding strata in the original space using nonlinear dimensionality reduction. We show that our approach is effective in high dimensions and can be used to further reduce the variance of multifidelity Monte Carlo estimators.

This book offers a hands-on introduction to building and understanding federated learning (FL) systems. FL enables multiple devices -- such as smartphones, sensors, or local computers -- to collaboratively train machine learning (ML) models, while keeping their data private and local. It is a powerful solution when data cannot or should not be centralized due to privacy, regulatory, or technical reasons. The book is designed for students, engineers, and researchers who want to learn how to design scalable, privacy preserving FL systems. Our main focus is on personalization: enabling each device to train its own model while still benefiting from collaboration with relevant devices. This is achieved by leveraging similarities between (the learning tasks associated with) devices that are encoded by the weighted edges (or links) of a federated learning network (FL network). The key idea is to represent real-world FL systems as networks of devices, where nodes correspond to device and edges represent communication links and data similarities between them. The training of personalized models for these devices can be naturally framed as a distributed optimization problem. This optimization problem is referred to as generalized total variation minimization (GTVMin) and ensures that devices with similar learning tasks learn similar model parameters. Our approach is both mathematically principled and practically motivated. While we introduce some advanced ideas from optimization theory and graph-based learning, we aim to keep the book accessible. Readers are guided through the core ideas step by step, with intuitive explanations.

Cyclone rapid intensification is the rapid increase in cyclone wind intensity, exceeding a threshold of 30 knots, within 24 hours. Rapid intensification is considered an extreme event during a cyclone, and its occurrence is relatively rare, contributing to a class imbalance in the dataset. A diverse array of factors influences the likelihood of a cyclone undergoing rapid intensification, further complicating the task for conventional machine learning models. In this paper, we evaluate deep learning, ensemble learning and data augmentation frameworks to detect cyclone rapid intensification based on wind intensity and spatial coordinates. We note that conventional data augmentation methods cannot be utilised for generating spatiotemporal patterns replicating cyclones that undergo rapid intensification. Therefore, our framework employs deep learning models to generate spatial coordinates and wind intensity that replicate cyclones to address the class imbalance problem of rapid intensification. We also use a deep learning model for the classification module within the data augmentation framework to di fferentiate between rapid and non-rapid intensification events during a cyclone. Our results show that data augmentation improves the results for rapid intensification detection in cyclones, and spatial coordinates play a critical role as input features to the given models. This paves the way for research in synthetic data generation for spatiotemporal data with extreme events. Introduction Over the past decade, the impacts of climate change have manifested in an alarming increase in the strength of tropical cyclones, characterised by elevated levels of precipitation and wind intensity, resulting in devastating consequences on a global scale [1, 2, 3]. Rappaport et al. [4] defined rapid intensification as a sudden surge in wind intensity exceeding 30 knots (35 miles / hour or 55 kilometres / hour) within 24 hours [5]. Forecasting the rapid intensification of high-category cyclones (Category 4 and 5) poses greater challenges due to their infrequent occurrence, in contrast to lower-category cyclones[6].

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information. Evaluating 20 frontier LLMs reveals abstention is an unsolved problem, and one where scaling models is of little use. While recent reasoning LLMs have shown impressive results in complex problem solving, surprisingly, we find that reasoning fine-tuning degrades abstention (by $24\%$ on average), even for math and science domains on which reasoning models are explicitly trained. We find that while a carefully crafted system prompt can boost abstention in practice, it does not resolve models' fundamental inability to reason about uncertainty. We release AbstentionBench to foster research into advancing LLM reliability.

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the injected knowledge. We present a hypernetwork-based approach for knowledge propagation, named PropMEND, where we meta-learn how to modify gradients of a language modeling loss to encourage injected information to propagate. Our approach extends the meta-objective of MEND [29] so that gradient updates on knowledge are transformed to enable answering multi-hop questions involving that knowledge. We show improved performance on the RippleEdit dataset, showing almost 2x accuracy on challenging multi-hop questions whose answers are not explicitly stated in the injected fact. We further introduce a new dataset, Controlled RippleEdit, to evaluate the generalization of our hypernetwork, testing knowledge propagation along relations and entities unseen during hypernetwork training. PropMEND still outperforms existing approaches in unseen entity-relation pairs, yet the performance gap decreases substantially, suggesting future work in propagating knowledge to a wide range of relations.

--Graph Neural Networks (GNNs) often struggle with heterophilic data, where connected nodes may have dissimilar labels, as they typically assume homophily and rely on local message passing. T o address this, we propose creating alternative graph structures by linking nodes with similar structural attributes (e.g., role-based or global), thereby fostering higher label homophily on these new graphs. We theoretically prove that GNN performance can be improved by utilizing graphs with fewer false positive edges (connections between nodes of different classes) and that considering multiple graph views increases the likelihood of finding such beneficial structures. Building on these insights, we introduce Structure-Guided GNN (SG-GNN), an architecture that processes the original graph alongside the newly created structural graphs, adaptively learning to weigh their contributions. Extensive experiments on various benchmark datasets, particularly those with heterophilic characteristics, demonstrate that our SG-GNN achieves state-of-the-art or highly competitive performance, highlighting the efficacy of exploiting structural information to guide GNNs. RAPH neural networks (GNNs) have demonstrated remarkable performance in processing graph-structured data by leveraging local neighborhood information [1], [2]. For node classification or regression, the graph structure is traditionally assumed to indicate which nodes should share similar representations or be treated similarly by a GNN. This holds true in many real-world scenarios; for example, temperature readings on a graph discretizing a geographical region often exhibit smoothness, where nearby sensors record similar temperatures [2]. M. Tenorio, S. Rey, and A. G. Marques are with the Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain.