The RMS Titanic sank in the North Atlantic Ocean on April 15, 1912, after colliding with an iceberg during her maiden voyage from Southampton to New York. More than 1,500 people died when the ship, which was carrying 2,224 passengers and crew, sank under the command of Captain Edward Smith. Some of the wealthiest people in the world were on board, including property tycoon John Jacob Astor IV, great grandson of John Jacob Astor, founder of the Waldorf Astoria Hotel. Millionaire Benjamin Guggenheim, heir to his family's mining business, also perished, along with Isidor Straus, the German-born co-owner of Macy's department store. The ship was the largest afloat at the time and was designed in such a way that it was meant to be'unsinkable'.

The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025) took place in Philadelphia from Tuesday 25 February to Tuesday 4 March 2025. The programme featured eight invited talks. Susan works at the intersection of computer science and economics. In the past she has researched problems relating to mechanism design, auctions, pricing, and causal inference, but recently she has turned her attention to modelling worker career transitions using transformer models. In her talk, Susan described the research in a few of her recent papers covering topics such as the gender wage gap and economic prediction of labour sequence data.

Kyiv, Ukraine – Thread-thin, glistening in the sun and kilometres long, optical fibres wind through the branches of trees on the frontlines of eastern Ukraine. The cords were – sometimes still are – attached to Russian drones, making them immune to radio-electronic jamming. The drones may have been shot down. Some are still operational, waylaid and replete with danger. "When somebody is passing by, they just fly up and attack," Oleh, a military officer deployed in eastern Ukraine, told Al Jazeera.

Rip currents are strong, localized and narrow currents of water that flow outwards into the sea, causing numerous beach-related injuries and fatalities worldwide. Accurate identification of rip currents remains challenging due to their amorphous nature and the lack of annotated data, which often requires expert knowledge. To address these issues, we present RipVIS, a large-scale video instance segmentation benchmark explicitly designed for rip current segmentation. RipVIS is an order of magnitude larger than previous datasets, featuring $184$ videos ($212,328$ frames), of which $150$ videos ($163,528$ frames) are with rip currents, collected from various sources, including drones, mobile phones, and fixed beach cameras. Our dataset encompasses diverse visual contexts, such as wave-breaking patterns, sediment flows, and water color variations, across multiple global locations, including USA, Mexico, Costa Rica, Portugal, Italy, Greece, Romania, Sri Lanka, Australia and New Zealand. Most videos are annotated at $5$ FPS to ensure accuracy in dynamic scenarios, supplemented by an additional $34$ videos ($48,800$ frames) without rip currents. We conduct comprehensive experiments with Mask R-CNN, Cascade Mask R-CNN, SparseInst and YOLO11, fine-tuning these models for the task of rip current segmentation. Results are reported in terms of multiple metrics, with a particular focus on the $F_2$ score to prioritize recall and reduce false negatives. To enhance segmentation performance, we introduce a novel post-processing step based on Temporal Confidence Aggregation (TCA). RipVIS aims to set a new standard for rip current segmentation, contributing towards safer beach environments. We offer a benchmark website to share data, models, and results with the research community, encouraging ongoing collaboration and future contributions, at https://ripvis.ai.

We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple diverse videos about real-world events, such as natural disasters or political elections. Videos are intuitive sources for retrieval-augmented generation (RAG), but most contemporary RAG workflows focus heavily on text and existing methods for video-based summarization focus on low-level scene understanding rather than high-level event semantics. To close this gap, we introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims, facilitating the integration of video into RAG pipelines and enabling the creation of in-depth content that is grounded in multimodal sources. We further propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos. CAG leverages an iterative interaction between an r1-style reasoning model and a VideoLLM to draw higher level inferences about the target event than is possible with VideoLLMs alone, which fixate on low-level visual features. We benchmark state-of-the-art VideoLLMs and CAG in both oracle retrieval and RAG settings and find that CAG consistently outperforms alternative methods, while suggesting intriguing avenues for future work.

Selective retrieval improves retrieval-augmented generation (RAG) by reducing distractions from low-quality retrievals and improving efficiency. However, existing approaches under-utilize the inherent knowledge of large language models (LLMs), leading to suboptimal retrieval decisions and degraded generation performance. To bridge this gap, we propose Self-Routing RAG (SR-RAG), a novel framework that binds selective retrieval with knowledge verbalization. SR-RAG enables an LLM to dynamically decide between external retrieval and verbalizing its own parametric knowledge. To this end, we design a multi-task objective that jointly optimizes an LLM on knowledge source selection, knowledge verbalization, and response generation. We further introduce dynamic knowledge source inference via nearest neighbor search to improve the accuracy of knowledge source decision under domain shifts. Fine-tuning three LLMs with SR-RAG significantly improves both their response accuracy and inference latency. Compared to the strongest selective retrieval baseline, SR-RAG reduces retrievals by 29% while improving the performance by 5.1%.

A Russian drone attack has killed at least four people and wounded 21 in the eastern Ukrainian city of Dnipro, damaging high-rise buildings and triggering fires in a hotel and homes, the regional governor said, as Moscow claims to have made gains on the ground elsewhere. Late Friday, Russia sent "more than two dozen drones" to Dnipro, the governor of the surrounding Dnipropetrovsk region, Sergiy Lysak, wrote on his official Telegram account on Saturday. "The massive attack caused large-scale destruction and fires. A hotel and restaurant complex, 11 private houses, garages, and a service station were on fire," he said, adding that high-rises and cars were also damaged. Pictures and videos posted online showed flames and large plumes of smoke wafting skyward.

Overnight, air sirens were heard sounding in several other Ukrainian regions, including the capital Kyiv. It was not immediately clear whether there were any casualties. The Russian military has not commented on the issue. In his video address late on Friday, Ukrainian President Volodymyr Zelensky again accused Russia of targeting Ukrainian energy infrastructure - in violation of a temporary moratorium agreed earlier this month in talks involving the US. Moscow has also repeatedly blamed Ukraine for attacking Russia's energy sector. Russian President Vladimir Putin earlier this week suggested that Ukraine should temporarily be placed under UN control to elect what he called a more "competent" government.

On March 18, the official White House account on X posted two photographs of Virginia Basora-Gonzalez, a woman who was arrested earlier this month by U.S. Immigration and Customs Enforcement. The post described her as a "previously deported alien felon convicted of fentanyl trafficking," and celebrated her capture as a win for the administration. In one photograph, Basora-Gonzalez is shown handcuffed and weeping in a public parking lot. The White House account posted about Basora-Gonzalez again yesterday--this time, rendering her capture in the animated style of the beloved Japanese filmmaker Hayao Miyazaki, who co-founded the animation company Studio Ghibli. Presumably, whoever runs the account had used ChatGPT, which has been going viral this week for an update to its advanced "4o" model that enables it to transform photographs in the style of popular art, among other things.

Oceanic processes at fine scales are crucial yet difficult to observe accurately due to limitations in satellite and in-situ measurements. The Surface Water and Ocean Topography (SWOT) mission provides high-resolution Sea Surface Height (SSH) data, though noise patterns often obscure fine scale structures. Current methods struggle with noisy data or require extensive supervised training, limiting their effectiveness on real-world observations. We introduce SIMPGEN (Simulation-Informed Metric and Prior for Generative Ensemble Networks), an unsupervised adversarial learning framework combining real SWOT observations with simulated reference data. SIMPGEN leverages wavelet-informed neural metrics to distinguish noisy from clean fields, guiding realistic SSH reconstructions. Applied to SWOT data, SIMPGEN effectively removes noise, preserving fine-scale features better than existing neural methods. This robust, unsupervised approach not only improves SWOT SSH data interpretation but also demonstrates strong potential for broader oceanographic applications, including data assimilation and super-resolution.