We introduce PLUME search, a data-driven framework that enhances search efficiency in combinatorial optimization through unsupervised learning. Unlike supervised or reinforcement learning, PLUME search learns directly from problem instances using a permutation-based loss with a non-autoregressive approach. We evaluate its performance on the quadratic assignment problem, a fundamental NP-hard problem that encompasses various combinatorial optimization problems. Experimental results demonstrate that PLUME search consistently improves solution quality. Furthermore, we study the generalization behavior and show that the learned model generalizes across different densities and sizes.

Artificial intelligence has gained widespread popularity and adoption across diverse industries due to its ability of automatic decision-making processes. In numerous contexts where artificial intelligence permeates various aspects of our lives, from business operations to societal dynamics and policy formulation, ensuring fairness is of greatest importance to meeting environmental, social, and governance standards. While for nearly any problem in the field of artificial intelligence, there can exist multiple measures of individual fairness as well as multiple measures of subgroup fairness. Often, Subgroup fairness involves multiple protected attributes (e.g., race, sex), creating numerous combinations of subgroups and corresponding subgroup fairness measures, all of which deserve consideration. Hence, it becomes essential to take into account the trade-offs among optimising for multiple fairness measures.

During a U.S. naval test off the California coast last month, which was designed to showcase the Pentagon's top autonomous drone boats, one vessel stalled unexpectedly. As officials scrambled to fix a software glitch, another drone vessel smashed into the idling boat's starboard side, vaulted over the deck, and crashed back into the water -- an incident captured in videos. The previously unreported episode, which involved two vessels built by U.S. defense tech rivals Saronic and BlackSea Technologies, is one of a series of recent setbacks in the Pentagon's push to build a fleet of autonomous vessels, according to a dozen people familiar with the program.

Lt. Gen. Keith Kellogg discusses the latest with the Ukraine and Russia war after a deadly Russian attack on'America Reports.' A Russian drone may have crashed in a field in Poland, a move the country's deputy prime minister called a "provocation," as the United States and European leaders continue to push Moscow to end its war in Ukraine. The drone hit a cornfield in the village of Osiny in the eastern Lublin province, about 62 miles from Poland's border with Ukraine, Reuters reported. Deputy Prime Minister Wladyslaw Kosiniak-Kamysz, who also serves as defense minister, said Wednesday's incident was similar to cases in which Russian drones flew into Lithuania and Romania, and could be linked to efforts to end the war in Ukraine, according to the outlet. Polish police secure the area of a cornfield where an unidentified flying object has crashed and exploded in the country's east in Osiny on Wednesday.

Such models, recently coined foundation models,h a v eb e e n transformational to the field of natural language processing.

Until now, radio communications, which require a clear line of sight between two antennas and use ultra-high frequency radios, have been relied upon to connect, say, astronauts on the surface of the Moon or a lunar lander with Earth. When Neil Armstrong and Buzz Aldrin stepped onto the Moon in 1969 they used a radio system called an S-Band, which used a lightweight umbrella-like antenna on the lunar lander to reflect signals over a vast distance. But with far more devices soon to populate the Moon's surface, and more advanced bandwidth-intensive and latency-sensitive applications, these technologies will fall short. As Klein outlines, there are multiple scenarios in which cellular connectivity that enables better range, more devices, and higher data transfer speeds will form the bedrock for safe, effective space exploration. For one, astronauts' work will need to be augmented by myriad robotic and autonomous systems--be it in drilling, mining, or harvesting for food--and each of these will need to coordinate and communicate with one another to align on tasks.

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data.

NATO Secretary General Mark Rutte gives insight on the talks between President Donald Trump, Volodymyr Zelenskyy and European leaders, security guarantees for Ukraine and more on'The Ingraham Angle.' Two German warplanes were scrambled overnight from Romania after Russia launched a large-scale missile and drone attack in Ukraine less than a mile from the NATO borderline. Romania's Ministry of Defense said on Wednesday that two German Eurofighter Typhoon aircraft, stationed at Romania's Mihail Kogălniceanu Air Base as part of NATO's Enhanced Air Policing mission, were deployed "to monitor the air situation," but noted that this time no Russian aircraft or projectiles crossed the NATO border. Despite last week's talks between Russian President Vladimir Putin and President Donald Trump, Moscow has continued its aerial bombardment of Ukraine, including in an overnight attack that targeted oil and port facilities in the Odesa region on and near the Danube River, which separates the Ukrainian border with the allied NATO nation of Romania. The Eurofighter EF-2000 Typhoon of the German Air Force takes off from Los Llanos military air base during the Tactical Leadership Program in Albacete, Spain, on Nov. 21, 2024. The deployment of NATO jets comes after numerous incidents in recent weeks have increasingly threatened, and even crossed, NATO borders as the U.S. and Europe continue to push for Russia to end its war.

An artificial intelligence model trained on NASA satellite imagery can forecast what the sun will look like hours into the future – even predicting the appearance of solar flares that may warn of dangerous space weather for Earth. "I love to think of this model as an AI telescope where you can look at the sun and you can understand the moods," says Juan Bernabé-Moreno at IBM Research Europe. The sun's moods matter because outbursts of solar activity can bombard Earth with high-energy particles, X-rays and extreme ultraviolet radiation. These can disrupt GPS and communications satellites, and potentially harm astronauts and even people on commercial airlines. Solar flares can be followed by coronal mass ejections, which may disrupt Earth's own magnetic field and create geomagnetic storms capable of knocking out power grids.

There's no way to prevent these sorts of effects, but being able to predict when a large solar flare will occur could let people work around them. However, as Louise Harra, an astrophysicist at ETH Zurich, puts it, "when it erupts is always the sticking point." Scientists can easily tell from an image of the sun if there will be a solar flare in the near future, says Harra, who did not work on Surya. But knowing the exact timing and strength of a flare is much harder, she says. That's a problem because a flare's size can make the difference between small regional radio blackouts every few weeks (which can still be disruptive) or a devastating solar superstorm that would cause satellites to fall out of orbit and electrical grids to fail.