A 17-year-old British sailor saved Simon from the Hong Kong docks when he was likely a year old. Breakthroughs, discoveries, and DIY tips sent six days a week. One day in March of 1948, George Hickinbottom, a British sailor, was walking around the docks of Stonecutters Island in Hong Kong. When the 17-year-old spotted a small black-and-white tuxedo cat, barely out of kittenhood, he decided to smuggle the hungry, scrawny animal aboard his ship, the HMS . Hickinbottom didn't get in trouble.

You've Never Heard of China's Greatest Sci-Fi Novel Thousands of authors. is barely known outside China--but it contains the secret to the country's modernization and malaise. Ma Qianzhu was unsatisfied with Chinese progress. An engineer at a large state-owned enterprise, he belonged to a generation that grew up believing engineering is destiny, that China's future would be built, bolt by bolt, by people like him. Then Ma discovered something extraordinary: a wormhole to the late Ming Dynasty. With more than 500 peers, he commandeered a ship and traveled back in time 400 years, to a preindustrial China wracked by foreign invasion and internal decay. Their mission: trigger an industrial revolution in the past that would, in the future, make modern China great (again).

Elon Musk is seeking between $79 billion and $134 billion in damages over his claims that OpenAI defrauded him by abandoning its nonprofit roots and partnering with Microsoft. Elon Musk wants OpenAI and Microsoft to pay him damages in the range of $79 billion to $134 billion over his claims that the generative AI company defrauded him by abandoning its nonprofit roots and partnering with the software giant. Musk's lawyer detailed the damages request in a court filing Friday, a day after a federal judge rejected a final bid by OpenAI and Microsoft to avoid a jury trial set for late April in Oakland, California. Citing calculations by a financial economist expert witness, C. Paul Wazzan, the filing says Musk is entitled to a chunk of OpenAI's current $500 billion valuation after he was defrauded of the $38 million in seed money he donated to OpenAI when he helped found the startup in 2015. OpenAI and Microsoft later disputed the calculations.

Two years ago, companies like Meta and OpenAI were united against military use of their tools. Now all of that has changed. At the start of 2024, Anthropic, Google, Meta, and OpenAI were united against military use of their AI tools. But over the next 12 months, something changed. In January, OpenAI quietly rescinded its ban on using AI for "military and warfare" purposes, and soon after it was reported to be working on "a number of projects" with the Pentagon. In November, in the same week that Donald Trump was reelected US president, Meta announced that the United States and select allies would be able to employ Llama for defense uses.

Traditional sea exploration faces significant challenges due to extreme conditions, limited visibility, and high costs, resulting in vast unexplored ocean regions. This paper presents an innovative AI-powered Autonomous Underwater Vehicle (AUV) system designed to overcome these limitations by automating underwater object detection, analysis, and reporting. The system integrates YOLOv12 Nano for real-time object detection, a Convolutional Neural Network (CNN) (ResNet50) for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and K-Means++ clustering for grouping marine objects based on visual characteristics. Furthermore, a Large Language Model (LLM) (GPT-4o Mini) is employed to generate structured reports and summaries of underwater findings, enhancing data interpretation. The system was trained and evaluated on a combined dataset of over 55,000 images from the DeepFish and OzFish datasets, capturing diverse Australian marine environments. Experimental results demonstrate the system's capability to detect marine objects with a mAP@0.5 of 0.512, a precision of 0.535, and a recall of 0.438. The integration of PCA effectively reduced feature dimensionality while preserving 98% variance, facilitating K-Means clustering which successfully grouped detected objects based on visual similarities. The LLM integration proved effective in generating insightful summaries of detections and clusters, supported by location data. This integrated approach significantly reduces the risks associated with human diving, increases mission efficiency, and enhances the speed and depth of underwater data analysis, paving the way for more effective scientific research and discovery in challenging marine environments.

Coral reefs are rapidly declining due to anthropogenic pressures such as climate change, underscoring the urgent need for scalable, automated monitoring. We introduce ReefNet, a large public coral reef image dataset with point-label annotations mapped to the World Register of Marine Species (WoRMS). ReefNet aggregates imagery from 76 curated CoralNet sources and an additional site from Al Wajh in the Red Sea, totaling approximately 925000 genus-level hard coral annotations with expert-verified labels. Unlike prior datasets, which are often limited by size, geography, or coarse labels and are not ML-ready, ReefNet offers fine-grained, taxonomically mapped labels at a global scale to WoRMS. We propose two evaluation settings: (i) a within-source benchmark that partitions each source's images for localized evaluation, and (ii) a cross-source benchmark that withholds entire sources to test domain generalization. We analyze both supervised and zero-shot classification performance on ReefNet and find that while supervised within-source performance is promising, supervised performance drops sharply across domains, and performance is low across the board for zero-shot models, especially for rare and visually similar genera. This provides a challenging benchmark intended to catalyze advances in domain generalization and fine-grained coral classification. We will release our dataset, benchmarking code, and pretrained models to advance robust, domain-adaptive, global coral reef monitoring and conservation.

Unlike traditional backdoor attacks that focus on specific class labels, our approach aims to induce poisoned models to predict future data as a predefined target pattern.

A new congressional report warns China's military buildup has reached a war footing with 350 new missile silos and 20% nuclear expansion, threatening U.S. deterrence.

Military experts warn that Chinese missile strikes on U.S. air bases could cripple American airpower in the Pacific, as both nations pursue different strategies for air superiority.

Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.