This paper studies the problem of safe meta-reinforcement learning (safe meta-RL), where an agent efficiently adapts to unseen tasks while satisfying safety constraints at all times during adaptation. We propose a framework consisting of two complementary modules: safe policy adaptation and safe meta-policy training. The first module introduces a novel one-step safe policy adaptation method that admits a closed-form solution, ensuring monotonic improvement, constraint satisfaction at every step, and high computational efficiency. The second module develops a Hessian-free meta-training algorithm that incorporates safety constraints on the meta-policy and leverages the analytical form of the adapted policy to enable scalable optimization. Together, these modules yield three key advantages over existing safe meta-RL methods: (i) superior optimality, (ii) anytime safety guarantee, and (iii) high computational efficiency. Beyond existing safe meta-RL analyses, we prove the anytime safety guarantee of policy adaptation and provide a lower bound of the expected total reward of the adapted policies compared with the optimal policies, which shows that the adapted policies are nearly optimal. Empirically, our algorithm achieves superior optimality, strict safety compliance, and substantial computational gains--up to 70\% faster training and 50\% faster testing--across diverse locomotion and navigation benchmarks.

The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on training binary classifiers, which depend heavily on the quantity and quality of available generated images. In this work, we propose a novel framework that exploits geometric differences between the data manifolds of natural and generated images. To exploit this difference, we employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones, leveraging the property that their gradients reside in mutually orthogonal subspaces. This design enables a simple yet effective detection method: an image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images. Further more, to address diminishing manifold disparities in advanced generative models, we leverage normalizing flows to amplify detectable differences by extruding generated images away from the natural image manifold. Extensive experiments demonstrate the efficacy of this method.

Self-attention has emerged as a fundamental component driving the success of modern transformer architectures, which power large language models and various applications. However, a theoretical understanding of how such models actually work is still under active development. The recent work of (Marion et al., 2025) introduced the so-called single-location regression problem, which can provably be solved by a simplified self-attention layer but not by linear models, thereby demonstrating a striking functional separation. A rigorous analysis of self-attention with softmax for this problem is challenging due to the coupled nature of the model. In the present work, we use ideas from the classical random energy model in statistical physics to analyze softmax self-attention on the single-location problem. Our analysis yields exact analytic expressions for the population risk in terms of the overlaps between the learned model parameters and those of an oracle. Moreover, we derive a detailed description of the gradient descent dynamics for these overlaps and prove that, under broad conditions, the dynamics converge to the unique oracle attractor. Our work not only advances our understanding of self-attention but also provides key theoretical ideas that are likely to find use in further analyses of even more complex transformer architectures.

Download this complimentary White Paper today! This White Paper gives engineers, researchers, and care professionals an overview of how socially assistive wellness robots can support senior wellness, and how a framework can measure their autonomy. What you will learn about:  Why the senior care crisis exceeds incremental healthcare automation. Staffing shortages, rising dementia prevalence, and limited daily wellness programming all play a part. How the seven ICAA dimensions of wellness define a distinct category of socially assistive robot, separate from companion devices, medical devices, and general-purpose humanoids. How the Care Robot Autonomy Scale (CRAS), a six-level framework modeled on a driving-automation standard, measures autonomy across four wellness dimensions. What technical capabilities, clinical evidence, and a three-phase roadmap suggest about the path from current practice toward full wellness autonomy in the early 2030s. Click 'LOOK INSIDE' to Download Now.

Trump's Border Crackdown Is Wreaking Havoc on the World Cup Travel bans and other visa issues are creating problems for World Cup participants even before the whistle blows. Even before the first whistle blows, the 2026 World Cup --taking place from June 11 to July 19 across the United States, Canada, and Mexico--already has winners and losers away from the field. Here, amidst denied visas, prolonged checks, and contested entries, a parallel competition is emerging where human rights are at stake. This World Cup was meant to be a global celebration of soccer in North America. For the first time in history, the tournament is being held in three different countries, a move meant to unite the entire continent and turn the World Cup into an even more inclusive event.

Soccer officials already rely on cameras to see who's offside and who sent the ball out of bounds. But during this World Cup, refs will use digital twins of each player to view plays from every angle. At the 2026 World Cup, the refs on the field and the officials on the sidelines will be able to use an abundance of tech to help call penalties, spot offside violations, and make other consequential decisions. The video assistant referee system, known as VAR, and the semi-automated offside technology (SAOT) have been used in soccer for years. But the setup at this summer's World Cup represents some of the most advanced uses of adjudication tech to date--not just in soccer, but across all high-level sports.

Many of the insights hitting soccer pitches today trace back to Jesse Davis and a team of computer scientists open-sourcing tools for some of the sport's trickiest problems. Imagine tuning in to the opening kickoff of a World Cup match and seeing a player intentionally send the ball all the way down the pitch and right out of bounds on the opponent's end. Casual fans might scratch their heads. If you were Jesse Davis, though, you'd know that this play could be a prime setup to score. Davis is a professor of computer science at KU Leuven in Belgium and head of its Sports Analytics Lab, which has been at the vanguard of a data awakening in soccer since its inception more than a decade ago. Though the research group brings machine-learning models to bear on a variety of sports--including basketball, volleyball, and field hockey--nowhere is its impact felt more than on the soccer pitch.

Venues hosting the 2026 World Cup must meet high standards to obtain environmental certifications, but FIFA also requires that they use natural grass, which is water-intensive to maintain. Estadio Banorte, formerly called Azteca stadium, in Mexico City. Because of their scale, soccer stadiums require a fair amount of energy and water. In that time, they also generate large volumes of waste, mainly plastics and food trash. For the 2026 World Cup, the first to be held in three countries in 16 different stadiums, FIFA maintained the requirement that the venues must have LEED environmental certifications, which measure performance in water, energy, and waste management.

Chemist Tim Cernak is using two decades of experience in Big Pharma to try to save Gila monsters, loggerhead sea turtles, and many more creatures. In 2018, after nearly two decades working in Big Pharma, chemist Tim Cernak was ready to put his skills to a new use. For Merck, he'd developed precision therapies for cancer, HIV, and diabetes that could target disease while minimizing harm to healthy cells. But as a lifelong nature lover, he was increasingly concerned about the health of ecosystems and wondered whether his expertise could transfer. Animals, he learned, are often treated with pharmaceuticals formulated for humans, which affect them like old-school cancer drugs: Though intended to kill abnormal cells, they're indiscriminate in the harm they cause. For instance, the standard of care for frogs infected with a deadly skin infection is itraconazole, an antifungal that is often lethal for the amphibian.

The games start June 11 and end with a grand finale in New Jersey on July 19. There are 104 of them. Here's how to watch'em all. The FIFA Men's World Cup is almost here, and this one will be the biggest ever. The tournament is hosted by three countries: Mexico, Canada, and the US.