After four weeks of using the cream, participants lowered the biological age of their skin by about two years on average. A wave of biotech companies is looking to prove that it's possible to slow down the aging process. Mountain View, California-based Rubedo Life Sciences is starting with the most outwardly visible sign: the skin. The company's experimental treatment is showing early promise that it may be able to reduce the appearance of aging, according to data the company presented at the Aging Research and Drug Discovery meeting in Boston earlier this month. In a small clinical trial, Rubedo tested its topical cream on 11 people with atopic dermatitis, an inflammatory skin condition and the most common type of eczema.

All those container ships and fishing vessels are only generating noise in the first place because there's a consumer downstream paying them to do so. By simply opting to purchase more goods locally, Fournet notes, everyday people can play at least a small part in reducing their overall contribution to ocean noise. In other words, a farmer's market apple might not just taste better; it's better for whales too. "In this case, sure, humans are the problem," Fournet adds. "Humans in this case are also the solution. We created this problem, but we do have the capacity to fix it."

Sometimes, AI-driven restructuring goes about as well as an AI-assisted legal brief. Reuters reports that Meta spent much of this year testing a plan in which AI would take over many of the workforce's daily tasks. Dubbed Project OT, the plan appears to connect two stories from earlier this year: Meta's 10 percent workforce reduction and the company's program that tracked employees' mouse movements and keystrokes. Meta executives were reportedly influenced by startups, including some they observed in Asia, that had structured themselves around AI. At an annual leadership retreat in January at Mark Zuckerberg's Hawaii estate, executives laid out an "AI native" vision for the company.

VAT will be cut from household electricity bills, the government has announced, as part of new Prime Minister Andy Burnham's pledge to help with the cost of living. The reduction from 5% VAT to zero will come into effect on 1 October, saving a typical household about £45 a year. Ministers said it would be funded by savings from the cancellation of the digital ID programme, which was going to cost £1.8bn The government estimated it will cost £850m this financial year . But Labour's Darren Jones, who was sacked as chief secretary to the prime minister on Monday, accused the government of announcing an unfunded tax cut.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Watermarking promises a statistical trace of large language model (LLM) use, but real documents, after editing or paraphrasing, rarely arrive as purely human-written or purely machine-generated. This motivates a quantitative question beyond detection: what proportion of a document is generated from a pre-specified watermarked LLM? We study this watermark proportion estimation problem under the Gumbel--max watermarking mechanism, treating the next-token prediction (NTP) distributions as unknown and arbitrary nuisance parameters subject to a non-degeneracy condition. We compare two observation regimes: in the full observation regime, the estimator observes the pseudorandom vector and the selected token at each position; under the more popular setting of pivotal reduction, it observes only a scalar pivot, which follows a one-dimensional Uniform--Beta mixture distribution. Under pivotal reduction, we develop a Laguerre-polynomial estimator and establish a matching information-theoretic lower bound for the sample complexity. For full observation, we introduce an event-counting estimator and show a matching lower bound, yielding a substantially smaller sample complexity. As our results imply, although reducing to pivotal statistics is an elegant and widely used procedure, it is not always sample-efficient for estimating the proportion of watermarks.

Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically rely on single-layer attention scores to rank and prune redundant visual tokens to solve this inefficiency. However, as the interaction between tokens and layers is complicated, this raises a basic question: Is such a simple single-layer criterion sufficient to identify redundancy? To answer this question, we rethink the emergence of redundant visual tokens from a fundamental perspective: information flow, which models the interaction between tokens and layers by capturing how information moves between tokens across layers. We find (1) the CLS token acts as an information relay, which can simplify the complicated flow analysis; (2) the redundancy emerges progressively and dynamically via layer-wise attention concentration; and (3) relying solely on attention scores from single layers can lead to contradictory redundancy identification. Based on this, we propose FlowCut, an information-flow-aware pruning framework, mitigating the insufficiency of the current criterion for identifying redundant tokens and better aligning with the model's inherent behaviors. Extensive experiments show FlowCut achieves superior results, outperforming SoTA by 1.6% on LLaVA-1.5-7B with 88.9% token reduction, and by 4.3% on LLaVA-NeXT-7B with 94.4% reduction, delivering 3.2$\times$ speed-up in the prefilling stage.

KV cache technology, by storing key-value pairs, helps reduce the computational overhead incurred by (LLMs).

The convergence of online learning algorithms in games under self-play is a fundamental question in game theory and machine learning. Among various notions of convergence, last-iterate convergence is particularly desirable, as it reflects the actual decisions made by the learners and captures the day-to-day behavior of the learning dynamics. While many algorithms are known to converge in the average-iterate, achieving last-iterate convergence typically requires considerably more effort in both the design and the analysis of the algorithm. Somewhat surprisingly, we show in this paper that for a large family of games, there exists a simple black-box reduction that transforms the average iterates of an uncoupled learning dynamics into the last iterates of a new uncoupled learning dynamics, thus also providing a reduction from last-iterate convergence to average-iterate convergence. Our reduction applies to games where each player's utility is linear in both their own strategy and the joint strategy of all opponents. This family includes two-player bimatrix games and generalizations such as multi-player polymatrix games. By applying our reduction to the Optimistic Multiplicative Weights Update algorithm, we obtain new state-of-the-art last-iterate convergence rates for uncoupled learning dynamics in multi-player zero-sum polymatrix games: (1) an $O(\frac{\log d}{T})$ last-iterate convergence rate under gradient feedback, representing an exponential improvement in the dependence on the dimension $d$ (i.e., the maximum number of actions available to either player); and (2) an $\tilde{O}(d^{\frac{1}{5}}T^{-\frac{1}{5}})$ last-iterate convergence rate under bandit feedback, improving upon the previous best rates of $\tilde{O}(\sqrt{d}T^{-\frac{1}{8}})$ and $\tilde{O}(\sqrt{d}T^{-\frac{1}{6}})$.

The company says its AI adoption and deployment may result in further reductions. Back in March, it was widely reported that Oracle had sent anywhere between 10,000 and 30,000 employees an email, notifying them that it was their last day with the company. Now, we have a more concrete number of people who had lost their jobs. In its annual regulatory filing, Oracle said that it employs approximately 141,000 people worldwide as of May 31, 2026. That's down 21,000 employees from the 162,000 people employed by the company in the same period last year.