Drone games put Ukraine's best military pilots to the test TRUSKAVETS, Ukraine - In the sky over western Ukraine, a bullet-shaped P1-SUN interceptor drone dived toward its target as dozens of soldiers looked on. A cheer went up as it cut through a tow line from another drone to a balloon, which drifted away. Ukraine's most skilled military drone pilots squared off this week not against Russia, but against each other in a competition to win bragging rights and state-of-the-art hardware for their units. Drone technology has transformed the war in Ukraine. Young men using video game consoles to operate strike drones packed with explosives -- sometimes from command centers far behind the front line -- are deeply feared by enemy soldiers.

Countries including Japan see the ability to control chips, data centers and AI models as directly related to national resilience in a landscape dominated by U.S. and Chinese technology. Sakura Internet's chief said the company may need to hike its capital spending by nearly seven times its initial plan to keep up with artificial intelligence demand in Japan. The data center operator is eyeing an allocation of as much as ¥20 billion to ¥30 billion ($125 million to $190 million) this fiscal year, founder and CEO Kunihiro Tanaka said. That's above the ¥4.4 billion in the Osaka-based company's official capital expenditure plan announced last month. "AI server usage rates are 80% to 90%," Tanaka, 48, said in an interview.

On London's streets, facial recognition tests the balance between security and liberty Temporary street signs warn pedestrians of a Metropolitan Police live facial recognition operation in London on May 11. | REUTERS London - Tourists, shoppers and office workers on a busy London street on an ordinary weekday found themselves part of a digital identity check as live facial recognition cameras scanned faces against a police watchlist. The operation was an example of a technology the Metropolitan Police say is transforming policing, helping officers arrest around 2,500 wanted people since the start of 2024, including suspects accused of violent and sexual offences. Critics, however, say live facial recognition undermines the presumption of innocence underpinning British law by treating every passerby as a potential suspect. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

How Saudi Arabia's spending spree reached the end of the line Autocratic monarchs once left an echo of their glory in the ruins of the megaprojects they commanded at the peak of their unchallenged power. Those monumental physical traces are to be found in the fertile plains, mountainsides and deserts of the Middle East. But one of their most prominent modern counterparts may only have a digital footprint to leave behind for some of his most ambitious concepts. A decade ago, the Crown Prince of Saudi Arabia Mohammed bin Salman - or MBS as he is widely known - decreed a revisioning of his country that leapt from the realm of science fiction. It was called Vision 2030. Extraordinary monolithic structures were to help bring forth new technological marvels not just for the Kingdom but for the world.

Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less costly, yet also less accurate, aggregate models. We introduce partial fusion of networks, which interpolates between ensembles and weight aggregation and thus allows for a flexible tradeoff between computational cost and performance. A direct way to achieve this is to extend existing weight aggregation methods based on neuron-level similarity between different networks, where partial fusion then only aggregates weights of neurons which are most similar. We showcase one particular method to jointly identify which neurons are most similar and match them via partial optimal transport. Further, we consider the more general perspective of weight aggregation and partial fusion as generalized pruning of ensemble models, where neurons cannot just be deleted, but also linearly combined. Finally, we show that generalized pruning applied to a single network yields similar benefits as partial fusion by allowing for a tradeoff between isolating, deleting, and linearly combining neurons based on similarity. Our code is available at https://github.com/Fabian-Mor/partial_fusion_nn.

Machine unlearning is a fundamental mechanism that enforces the right to be forgotten. Existing unlearning studies that rely on label manipulation or task-gradient reversal often deliver limited unlearning effectiveness. Moreover, they can undermine the original learning objective and typically do not guarantee equivalence to standard unlearning by retraining. In this paper, we propose \textbf{ManiF-SMC} (\textbf{Mani}fold \textbf{F}orgetting with \textbf{S}elf \textbf{M}ode \textbf{C}onnectivity), motivated by the observation that a model retrained on the remaining data tends to classify erased samples by their semantic similarity to the retained data. We begin with systematically recasting the approximate unlearning as pushing each erased sample away from its original learned manifold representation centroid toward its nearest semantic neighbors in the retained data. This reformulation aligns unlearning with retraining behavior and operates purely in representation space, reducing reliance on labels and task-specific gradients. To tackle the manifold representation-based unlearning problem, ManiF-SMC encapsulates the unlearning and representation preservation goals in a margin-based triplet loss. Because finding a suitable margin for unlearning is challenging, we propose a self-mode-connectivity module that rapidly reconstructs the local manifold to guide the adaptive margins generation for each unlearning case. Extensive experiments on four representative datasets show that ManiF-SMC achieves unlearning effectiveness comparable to state-of-the-art approximate methods while operating solely within the model's representation space.

Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decision risks, and human feedback. We propose Human-Centered Learning Mechanics (HCLM), a dynamical and information-theoretic framework for open and controlled learning systems. The central idea is that entropy regularization is useful only when the chosen entropy surrogate generates a non-degenerate information force along the optimization trajectory. Otherwise, entropy terms may produce weak, unstable, or misaligned gradients, causing the dynamics to collapse toward ordinary loss minimization. We introduce the notion of effective entropy and study tractable geometric entropy surrogates, including variance-based and log-determinant covariance proxies. The paper makes three contributions. First, it formalizes entropy regularization through effective information force and characterizes degenerate entropy regimes. Second, it derives convergence, entropy-flow, Wasserstein-gradient-flow, and noisy-representation generalization results under explicit assumptions. Third, it offers a conditional dynamical interpretation of scaling-law-like behavior as a balance between information injection, entropy dissipation, and residual risk, without claiming an unconditional derivation of empirical neural scaling laws. Controlled representation-learning experiments support the hypothesis that geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces than softmax-normalized entropy.

Figure AI says three humanoid robots named Bob, Frank and Gary ran autonomously for over 24 hours, sorting packages without human control in a warehouse test.

Man finds poop on his roof, and if that wasn't bad enough, it led to a mountain lion encounter Sydney Thomas dominates the red carpet in Cannes as her star continues to rise, new MLB power couple & MEAT! Viral staff photo reveals just how bloated Stephen Colbert's'Late Show' operation really was Four of the most controversial television finales in honor of'The Boys' despised ending Sophie Cuningham has heads spinning with her pregame outfit, Colbert's final jab & lessons from Kyle Busch Adrenaline-packed preview released for upcoming D-Day film'Pressure,' features loaded cast Kacey Musgraves responds to'fat activist' furious because she can't fit into her new Walmart clothing line Selena Gomez is reportedly bringing her talents to award-winning director's new four-hour X-rated movie Minka Kelly uncorks a heater at 45, ABS backfires spectacularly and LSU parents vs a security guard! Robot's lifeless corpse hauled off stage after fall during disastrous Michael Jackson impression Bear cubs spar on woman's front porch in adorable viral nature video, reactions pour in Sen Barrasso details Trump's nearly finalized Iran deal, stance on Strait of Hormuz We must'forget our personal differences' and get back to work: Sen Tommy Tuberville They obviously didn't get the memo here about Memorial Day Weekend being unofficial start of summer. It's cool this morning and it's not even supposed to get into the 80s today. But you know who did receive the memo?

Fake CAPTCHA checks are tricking people into installing malware by asking them to press keyboard shortcuts that execute hidden malicious scripts on their PCs.