Automating radiology report generation poses a dual challenge: building clinically reliable systems and designing rigorous evaluation protocols. We introduce a multi-agent reinforcement learning framework that serves as both a benchmark and evaluation environment for multimodal clinical reasoning in the radiology ecosystem. The proposed framework integrates large language models (LLMs) and large vision models (LVMs) within a modular architecture composed of ten specialized agents responsible for image analysis, feature extraction, report generation, review, and evaluation. This design enables fine-grained assessment at both the agent level (e.g., detection and segmentation accuracy) and the consensus level (e.g., report quality and clinical relevance). We demonstrate an implementation using chatGPT-4o on public radiology datasets, where LLMs act as evaluators alongside medical radiologist feedback. By aligning evaluation protocols with the LLM development lifecycle, including pretraining, finetuning, alignment, and deployment, the proposed benchmark establishes a path toward trustworthy deviance-based radiology report generation.

Low-cost mobile sensors can be used to collect PM$_{2.5}$ concentration data throughout an entire city. However, identifying air pollution hotspots from the data is challenging due to the uneven spatial sampling, temporal variations in the background air quality, and the dynamism of urban air pollution sources. This study proposes a method to identify urban PM$_{2.5}$ hotspots that addresses these challenges, involving four steps: (1) equip citizen scientists with mobile PM$_{2.5}$ sensors while they travel; (2) normalise the raw data to remove the influence of background ambient pollution levels; (3) fit a Gaussian process regression model to the normalised data and (4) calculate a grid of spatially explicit 'hotspot scores' using the probabilistic framework of Gaussian processes, which conveniently summarise the relative pollution levels throughout the city. We apply our method to create the first ever map of PM$_{2.5}$ pollution in Kigali, Rwanda, at a 200m resolution. Our results suggest that the level of ambient PM$_{2.5}$ pollution in Kigali is dangerously high, and we identify the hotspots in Kigali where pollution consistently exceeds the city-wide average. We also evaluate our method using simulated mobile sensing data for Beijing, China, where we find that the hotspot scores are probabilistically well calibrated and accurately reflect the 'ground truth' spatial profile of PM$_{2.5}$ pollution. Thanks to the use of open-source software, our method can be re-applied in cities throughout the world with a handful of low-cost sensors. The method can help fill the gap in urban air quality information and empower public health officials.

The growing demand for reliable electricity in universities necessitates intelligent energy management. This study proposes a machine learning-based load shedding framework for the University of Lagos, designed to optimize distribution and reduce waste. The methodology followed three main stages. First, a dataset of 3,648 hourly records from 55 buildings was compiled to develop building-level consumption models. Second, Principal Component Analysis was applied for dimensionality reduction, and clustering validation techniques were used to determine the optimal number of demand groups. Mini-Batch K-Means was then employed to classify buildings into high-, medium-, and low-demand clusters. Finally, short-term load forecasting was performed at the cluster level using multiple statistical and deep learning models, including ARIMA, SARIMA, Prophet, LSTM, and GRU. Results showed Prophet offered the most reliable forecasts, while Mini-Batch K-Means achieved stable clustering performance. By integrating clustering with forecasting, the framework enabled a fairer, data-driven load shedding strategy that reduces inefficiencies and supports climate change mitigation through sustainable energy management.

We introduce FreqRank, a mutation-based defense to localize malicious components in LLM outputs and their corresponding backdoor triggers. FreqRank assumes that the malicious sub-string(s) consistently appear in outputs for triggered inputs and uses a frequency-based ranking system to identify them. Our ranking system then leverages this knowledge to localize the backdoor triggers present in the inputs. We create nine malicious models through fine-tuning or custom instructions for three downstream tasks, namely, code completion (CC), code generation (CG), and code summarization (CS), and show that they have an average attack success rate (ASR) of 86.6%. Furthermore, FreqRank's ranking system highlights the malicious outputs as one of the top five suggestions in 98% of cases. We also demonstrate that FreqRank's effectiveness scales as the number of mutants increases and show that FreqRank is capable of localizing the backdoor trigger effectively even with a limited number of triggered samples. Finally, we show that our approach is 35-50% more effective than other defense methods.

The exponential development of generative artificial intelligence (GenAI) technologies like ChatGPT has raised increasing curiosity about their use in higher education, specifically with respect to how students view them, make use of them, and the implications for learning outcomes. This paper employs a hybrid methodological approach involving a systematic literature review and simulation-based modeling to explore student perceptions of GenAI use in the context of higher education. A total of nineteen empirical articles from 2023 through 2025 were selected from the PRISMA-based search targeting the Scopus database. Synthesis of emerging patterns from the literature was achieved by thematic categorization. Six of these had enough quantitative information, i.e., item-level means and standard deviations, to permit probabilistic modeling. One dataset, from the resulting subset, was itself selected as a representative case with which to illustrate inverse-variance weighting by Monte Carlo simulation, by virtue of its well-designed Likert scale format and thematic alignment with the use of computing systems by the researcher. The simulation provided a composite "Success Score" forecasting the strength of the relationship between student perceptions and learning achievements. Findings reveal that attitude factors concerned with usability and real-world usefulness are significantly better predictors of positive learning achievement than affective or trust-based factors. Such an interdisciplinary perspective provides a unique means of linking thematic results with predictive modelling, resonating with longstanding controversies about the proper use of GenAI tools within the university.

How is Russia replenishing its military? What is a'coalition of the willing'? How China forgot promises and'debts' to Ukraine How are Europe, the US pulling apart on Ukraine? Copenhagen airport shut after sighting of'unidentified drones' Authorities in Denmark have closed Copenhagen airport after unidentified drones were sighted nearby, causing about 15 flights to be diverted, police and airport officials told the AFP news agency. "The airspace over Copenhagen airport has been closed since 8:30pm (18:30 GMT) due to two to three unidentified drones. No aircraft can take off or land," airport spokeswoman Lise Agerley Kurstein said.

Trump drops bombshell Tylenol autism announcement as he vows to rip up'disgraceful' vaccine schedule in major medical shake-up Jimmy Kimmel Live! will return TOMORROW after host was canned over Charlie Kirk comments Tylenol maker responds to Trump's plans to link everyday drug to autism The six hidden messages in the texts between Charlie Kirk's'assassin' and his trans lover DECODED Top plastic surgeon reveals secrets behind Catherine Zeta-Jones' youthful appearance: 'This isn't what happens when we age' Common kitchen spice may reverse Alzheimer's disease, study suggests Barack and Michelle Obama arrive apart on Spielberg's yacht after ex-president's startling marriage confession Miley Cyrus shares the medicine that has kept her'grounded in a sober lifestyle' for 5 years Jimmy Kimmel steps in to'protect' Ivanka Trump from handsy comedian in resurfaced video Seven charities including Teenage Cancer Trust cut ties with Sarah Ferguson after leaked email showed her apologising to'supreme friend' Jeffrey Epstein Heather Locklear fans can't believe how amazing the Melrose Place vet looks at 63... 40 years after fame hit'Brazilian Josef Fritzl' makes chilling claim to police after'holding stepdaughter captive for 22 years' American'sexpert' deported from Indonesia after furious Muslim officials accused her of hosting KAMA SUTRA demonstrations Beloved actress who played loud, loving matriarch in 2002 romcom makes rare outing in LA...can you guess who? Face of man who tried to'murder Jeffrey Epstein' days before pedophile financier's mysterious suicide Candace Owens says she'll make Brigitte Macron submit to MEDICAL EXAM after'French first lady is a man' claim sparked lawsuit Blindfolded and awaiting death: Horrifying footage shows Hamas executing'Israeli collaborators' in Gaza streets as baying crowd screams'Allahu Akbar' All the'Biblical signs' pointing to the Rapture coming TOMORROW as believers spread fears the end is nigh New'loaded water' trend slashes cravings so you can lose weight... as expert reveals how to maximize benefits Clear and startling images of what appears to be a UFO were captured over Los Angeles, sparking fresh debate about what's flying over America's biggest cities. A pair of Los Angeles residents were on their balcony when they spotted a black, V-shaped craft covered in lights moving slowly over the city on August 28. The sighting went on for roughly 25 minutes, with the UFO flying south until the witnesses eventually lost sight of it around 11:38pm local time (2:38am ET). The pair was able to capture both pictures and clear videos with a cellphone camera, zooming in to see nine white lights along the UFO's hull.

'Done properly, AI releases human capacity,' Simon Stiell said. 'Done properly, AI releases human capacity,' Simon Stiell said. AI'carries risks' but will help tackle global heating, says UN's climate chief Mon 22 Sep 2025 15.54 EDTLast modified on Mon 22 Sep 2025 16.04 EDT Harnessing artificial intelligence will help the world to tackle the climate crisis, but governments must step in to regulate the technology, the UN's climate chief has said. AI is being used to make energy systems more efficient, and to develop tools to reduce carbon from industrial processes. The UN is also using AI as an aid to climate diplomacy.

US tech giant Nvidia will invest up to $100bn (£73bn) in OpenAI, the firm behind ChatGPT, the companies announced. Nvidia said it will supply high-performance chips needed for the processing power required by artificial intelligence (AI), of which OpenAI is a specialist. Described as a strategic partnership by Nvidia, it is the latest move by two high profile tech firms in the global AI race, where China is an emerging rival. The announcement comes after a series of high-profile investments by Nvidia, including a $5bn investment in Intel and a £2bn investment in the UK's AI sector. Nvidia said its latest investment will go towards growing data centres for OpenAI's next-generation AI infrastructure.

What is the H-1B visa programme? The White House Peace Vigil is dismantled - why? Who said what at Charlie Kirk's memorial? Chipmaker Nvidia will invest up to $100bn in OpenAI and provide it with data center chips, a tie-up between two of the highest-profile leaders in the global artificial intelligence (AI) race. The deal, announced on Monday, will see Nvidia start delivering chips as soon as late 2026 and will involve two separate but intertwined transactions, according to a person close to OpenAI. The first $10bn of Nvidia's investment in OpenAI, which was most recently valued at $500bn, will begin when the two companies reach a definitive agreement for OpenAI to purchase Nvidia chips. Nvidia did not respond to immediate requests for clarification about the deal.