When you purchase through links in our articles, we may earn a small commission. Microsoft wants to redefine the Windows AI PC. Copilot Actions is the first step. Microsoft's Copilot Actions is what happens when Microsoft begins rethinking the future of Windows and how AI is integrated into the operating system. Imagine agentic AI being turned loose inside your PC and performing tasks without your supervision.

Spotify partnering with multinational music companies to develop'responsible' AI products The market-leading music streamer is collaborating with the Sony, Universal and Warner music groups - whose combined rosters feature artists including Beyoncé, Ed Sheeran and Taylor Swift - to create new AI features. The tension between the music industry and some tech firms has already led to three major labels suing AI companies whose tools create music from user prompts. If the music industry doesn't lead in this moment, AI-powered innovation will happen elsewhere, without rights, consent, or compensation." Both Udio and Suno have said their technology is designed to generate new musical output and does not reproduce specific artists' work. The head of Universal Music Group, Sir Lucian Grainge, wrote in a memo to staff this week that Universal would seek an artist's consent before licensing use of their voice or existing songs to an AI company.

Plus: Meta has taken down a group dedicated to tracking ICE officers' movements An emerging field of science is seeking to use cell analysis to predict what kind of a person an embryo might eventually become. Some parents turn to these tests to avoid passing on devastating genetic disorders that run in their families. A much smaller group, driven by dreams of Ivy League diplomas or attractive, well-behaved offspring, are willing to pay tens of thousands of dollars to optimize for intelligence, appearance, and personality. But customers of the companies emerging to provide it to the public may not be getting what they're paying for. This story is from our forthcoming print issue, which is all about the body. Plus, you'll also receive a free digital report on nuclear power.

For patients with inflammatory bowel disease, antibiotics can be a double-edged sword. The broad-spectrum drugs often prescribed for gut flare-ups can kill helpful microbes alongside harmful ones, sometimes worsening symptoms over time. When fighting gut inflammation, you don't always want to bring a sledgehammer to a knife fight. Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and McMaster University have identified a new compound that takes a more targeted approach. The molecule, called enterololin, suppresses a group of bacteria linked to Crohn's disease flare-ups while leaving the rest of the microbiome largely intact.

Tokyo police believe the man made about 20,000 sexually explicit images of 262 women, such as actors and idols, and amassed sales of ¥1.2 million between October last year and September this year. Tokyo police have arrested a 31-year-old man for allegedly creating fake sexual images of female celebrities with generative artificial intelligence technology and displaying them online, it was learned Thursday. It is the first time that police in Japan have cracked down on sexual deepfake images of celebrities created with generative AI. The suspect, Hiroya Yokoi of the city of Akita, has admitted he began making deepfakes to earn a small amount of money, which he used to cover living expenses and repay a student loan. Authorities believe Yokoi made a total of about 20,000 sexually explicit images of 262 women, such as actors, television personalities and idols, and amassed sales of ¥1.2 million between October last year and September this year.

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. With your current subscription plan you can comment on stories. However, before writing your first comment, please create a display name in the Profile section of your subscriber account page. Your subscription plan doesn't allow commenting.

Accurate prediction of vehicle collision dynamics is crucial for advanced safety systems and post-impact control applications, yet existing methods face inherent trade-offs among computational efficiency, prediction accuracy, and data requirements. This paper proposes a dual Physics-Informed Neural Network framework addressing these challenges through two complementary networks. The first network integrates Gaussian Mixture Models with PINN architecture to learn impact force distributions from finite element analysis data while enforcing momentum conservation and energy consistency constraints. The second network employs an adaptive PINN with dynamic constraint weighting to predict post-collision vehicle dynamics, featuring an adaptive physics guard layer that prevents unrealistic predictions whil e preserving data-driven learning capabilities. The framework incorporates uncertainty quantification through time-varying parameters and enables rapid adaptation via fine-tuning strategies. Validation demonstrates significant improvements: the impact force model achieves relative errors below 15.0% for force prediction on finite element analysis (FEA) datasets, while the vehicle dynamics model reduces average trajectory prediction error by 63.6% compared to traditional four-degree-of-freedom models in scaled vehicle experiments. The integrated system maintains millisecond-level computational efficiency suitable for real-time applications while providing probabilistic confidence bounds essential for safety-critical control. Comprehensive validation through FEA simulation, dynamic modeling, and scaled vehicle experiments confirms the framework's effectiveness for Precision Immobilization Technique scenarios and general collision dynamics prediction.

Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models (LLMs) show potential in personalizing learning experiences, existing approaches often lack mechanisms for goal-aligned planning. We introduce Pxplore, a novel framework for PLPP that integrates a reinforcement-based training paradigm and an LLM-driven educational architecture. We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals. We train the policy combining supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), and deploy it within a real-world learning platform. Extensive experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths. We release our code and dataset to facilitate future research.

We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.

With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--"write like me"--has become a rapidly growing area of interest. However, style personalization is highly specific, relative to every user, and depends strongly on the pragmatic context, which makes it uniquely challenging. Although prior research has introduced benchmarks and metrics for this area, they tend to be non-standardized and have known limitations (e.g., poor correlation with human subjects). LLMs have been found to not capture author-specific style well, it follows that the metrics themselves must be scrutinized carefully. In this work we critically examine the effectiveness of the most common metrics used in the field, such as BLEU, embeddings, and LLMs-as-judges. We evaluate these metrics using our proposed style discrimination benchmark, which spans eight diverse writing tasks across three evaluation settings: domain discrimination, authorship attribution, and LLM-generated personalized vs non-personalized discrimination. We find strong evidence that employing ensembles of diverse evaluation metrics consistently outperforms single-evaluator methods, and conclude by providing guidance on how to reliably assess style-personalized text generation.