Clinical risk prediction plays a crucial role in early disease detection and personalized intervention. While recent models increasingly incorporate multimodal data, their development typically assumes access to large-scale, multimodal datasets and substantial computational resources. In practice, however, most clinical sites operate under resource constraints, with access limited to EHR data alone and insufficient capacity to train complicated models. This gap highlights the urgent need to democratize clinical risk prediction by enabling effective deployment in data-and resource-limited local clinical settings. In this work, we propose a cross-cohort cross-modal knowledge transfer framework that leverages the multimodal model trained on a nationwide cohort and adapts it to local cohorts with only EHR data. We focus on EHR and genetic data as representative multimodal inputs and address two key challenges. First, to mitigate the influence of noisy or less informative biological signals, we propose a novel mixture-of-aggregations design to enhance the modeling of informative and relevant genetic features. Second, to support rapid model adaptation in low-resource sites, we develop a lightweight graph-guided fine-tuning method that adapts pretrained phenotypical EHR representations to target cohorts using limited patient data. Extensive experiments on real-world clinical data validate the effectiveness of our proposed model.

Officer accused of using AI to'create evidence' Police have launched a criminal investigation into an officer accused of using artificial intelligence (AI) systems to create evidential material in a number of cases. The Derbyshire Police officer has been removed from frontline duties, pending the outcome of the investigation, said the force. The officer is alleged to have perverted the course of justice, but no arrests have been made, said police. A Crown Prosecution Service spokesperson said they were working with police, adding: We are engaging with defence teams and the courts in appropriate cases. They added: As police inquiries continue, it would not be appropriate to comment further.

The issue of AI sovereignty was in focus at London Tech Week. The issue of AI sovereignty was in focus at London Tech Week. UK sets out AI infrastructure push at London Tech Week - how does it stack up? Ownership of the commanding heights of the AI economy is a political talking point around the world, as countries seek to assert some control of a technology dominated by the US and China. London Tech Week, the showcase event for the UK tech industry, focused heavily on that theme this week.

Tim Smith: 'Today's short-form, fast-paced, highly captivating content may affect children's attention, comprehension and emotional response'. Tim Smith: 'Today's short-form, fast-paced, highly captivating content may affect children's attention, comprehension and emotional response'. Pioneering UK Nerve Lab harnesses AI to map effect of children's screen time P arents are constantly being told to limit their children's screen time. A relatively slow-paced programme such as Bluey offers a very different viewing experience to a fast-moving action series such as PAW Patrol, yet both are broadly considered suitable for young children. This challenge is growing as the type of content children are exposed to evolves.

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? Smart Alerts: Get notified about major news as it happens.

Plus, the next game from the Mouthwashing devs and trying to survive as a sentient guitar. Welcome to our latest roundup of what's going on in the indie game space. However, we've still got some neat new games that you can play this weekend to highlight, and news on a bunch of intriguing upcoming titles that might have slipped under your radar during SGF. Before all of that, I have game bundles to tell you about. Inkle has offered up a collection of all of its games (and the four-part novelization of) on Humble Bundle .

After WIRED reported last week that Meta's smart glasses app contained code that would enable the company to activate face-recognition features on the devices, the company removed the code this week without commenting on why or whether it plans to add such functionality back into the app later. Another WIRED investigation this week found that xAI's Grok is still hosting sexualized deepfakes, including "nudified" images and videos, of celebrities and at least one prominent US politician. After limiting the release of its new Mythos-class AI model over concerns about its potential impacts on cybersecurity, Anthropic announced a model upgrade for partners in its limited-access group this week and launched a "safe" version of the model to the public with guardrails meant to keep the system from being used to fuel cyberattacks. Meanwhile, the United States Cybersecurity and Infrastructure Security Agency issued a new directive to federal agencies this week in reaction to new AI threats that includes a requirement to fix the most urgent software vulnerabilities in as little as three days. As Europe looks to separate and insulate itself from US Big Tech, WIRED created a timeline that tracks all the ways EU governments, companies, and other organizations are moving away from US tech.

RJ Scaringe, the CEO of Rivian Automotive, joined us for a wide-ranging interview about how his company's new electric SUV fits into the current EV industry, and what comes next. RJ Scaringe got his PhD from MIT studying internal combustion engines. Then he founded a company to make them obsolete. In 2009, fresh out of grad school, he launched what would become Rivian. The company spent nearly a decade in stealth mode before arriving at the 2018 LA Auto Show with two electric rides nobody had seen coming. The road, however, hasn't been easy. Rivian lost $3.6 billion in 2025, and has burned through nearly $25 billion in the past eight years. It has spent more money over the same period than almost every other pure EV maker. Rivian's IPO was the largest worldwide in 2021, and one of the largest in US history, within days valuing the company at over $100 billion. Its stock has dropped from a high of $130 to around $16. Since the R1 went on sale in 2021, Rivian has sold 175,000 cars.

Monitoring chemical processes is essential to prevent catastrophic failures, optimize costs and profits, and ensure the safety of employees and the environment. A key component of modern monitoring systems is the automated detection of anomalies in sensor data over time, called time series, enabling partial automation of plant operation and adding additional layers of supervision to crucial components. The development of anomaly detection methods in this domain is challenging, since real chemical process data are usually proprietary, and simulated data are generally not a sufficient replacement. In this paper, we present NoBOOM, the first collection of datasets for anomaly detection in real-world chemical process data, including labeled data from a running process at our industry partner BASF SE -- one of the world's leading chemical companies -- and several chemical processes run in laboratory scale and pilot scale plants. While we are not able to share every detail about the industrial process, for the laboratory and pilot scale plants, we provide comprehensive information on plant configuration, process operation, and, in particular, anomaly events, enabling a differentiated analysis of anomaly detection methods. To demonstrate the complexity of the benchmark, we analyze the data with regard to common issues of time-series anomaly detection (TSAD) benchmarks, including potential triviality and bias.

In many real-world applications, deployed models encounter inputs that differ from the data seen during training. Open-world recognition ensures that such systems remain robust as ever-emerging, previously _unknown_ categories appear and must be addressed without retraining.Foundation and vision-language models are pre-trained on large and diverse datasets with the expectation of broad generalization across domains, including medical imaging.However, benchmarking these models on test sets with only a few common outlier types silently collapses the evaluation back to a closed-set problem, masking failures on rare or truly novel conditions encountered in clinical use.We therefore present NOVA, a challenging, real-life _evaluation-only_ benchmark of $\sim$900 brain MRI scans that span 281 rare pathologies and heterogeneous acquisition protocols. Each case includes rich clinical narratives and double-blinded expert bounding-box annotations. Together, these enable joint assessment of anomaly localisation, visual captioning, and diagnostic reasoning. Because NOVA is never used for training, it serves as an _extreme_ stress-test of out-of-distribution generalisation: models must bridge a distribution gap both in sample appearance and in semantic space.