In recent years, large language models (LLMs) have shown remarkable performance in many problems. However, they fail to plan reliably. Specialized attempts to improve their planning capabilities still produce incorrect plans and fail to generalize to larger tasks. Furthermore, LLMs designed for explicit "reasoning" fail to compete with automated planners while increasing computational costs, which reduces one of the advantages of using LLMs. In this paper, we show how to use LLMs to always generate correct plans, even for out-of-distribution tasks of increasing size.

Fair classification is a critical challenge that has gained increasing importance due to international regulations and its growing use in high-stakes decision-making settings. Existing methods often rely on adversarial learning or distribution matching across sensitive groups; however, adversarial learning can be unstable, and distribution matching can be computationally intensive. To address these limitations, we propose a novel approach based on the characteristic function distance. Our method ensures that the learned representation contains minimal sensitive information while maintaining high effectiveness for downstream tasks. By utilizing characteristic functions, we achieve a more stable and efficient solution compared to traditional methods. Additionally, we introduce a simple relaxation of the objective function that guarantees fairness in common classification models with no performance degradation. Experimental results on benchmark datasets demonstrate that our approach consistently matches or achieves better fairness and predictive accuracy than existing methods. Moreover, our method maintains robustness and computational efficiency, making it a practical solution for real-world applications.

Environment Animals Pets Dogs Mysterious Amazonian'ghost dog' caught on camera This wild short-eared canine is not your average pup. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The short-eared dog spotted by a camera trap in Bolivia. Breakthroughs, discoveries, and DIY tips sent six days a week. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

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?

Bogota - Colombians vote Sunday in a presidential election that will determine the conflict-ridden nation's response to spiraling violence, either staying left and opting for dialogue or tacking right towards all-out war. The constitution forbids a second term for the country's first-ever leftist President Gustavo Petro, whose "total peace" strategy has failed to negotiate an end to conflict with armed groups. Despite his absence from the ballot, "the campaign revolves around Petro," said Yann Basset, political science professor at Bogota's University of Rosario. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right. With your current subscription plan you can comment on stories.

'Hear them before I see them': How drones strike fear in Colombia Increasingly, armed groups in Colombia are turning to cheap, widely available drones to fight from a distance. What is the toll on civilians? Military surveillance drones fly in formation past an air traffic control tower in Colombia [Courtesy of Colombia's Batallon de Aeronaves No Tripuladas] Military surveillance drones fly in formation past an air traffic control tower in Colombia [Courtesy of Colombia's Batallon de Aeronaves No Tripuladas] She instinctively reaches for her young son. The noise always emerges from a small mountain behind her home, part of a tree-quilted landscape stitched with winding rivers along Colombia's border with Venezuela. I always hear them before I see them, if I see them at all, she says.

Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to make key design choices. In order to mitigate this issue, we introduce the Representation Gap, a metric closely related to the generalization error, but admitting better-behaved asymptotic dynamics. Focusing on equivariant diffusion models and leveraging results from optimal quantization and point-process theory, we derive a precise asymptotic equivalent of the Representation Gap and show that it is governed by a single parameter, the \textit{intrinsic dimension} of the task, which is easy to interpret, efficient to estimate, and can be linked to the equivariances of common neural network architectures. We show that this asymptotic dynamic also extends to a broader range of tasks and training algorithms. Finally, we demonstrate empirically that our asymptotic law and intrinsic dimension estimation are accurate on a wide range of synthetic datasets, where these quantities are known, as well as on more realistic datasets, where we obtain results consistent with the related literature.

Air France and Airbus have been found guilty of manslaughter over a 2009 plane crash which killed 228 people. The Paris Appeals Court found the airline and aircraft manufacturer guilty of corporate manslaughter over the incident, in which flight AF447 between Rio de Janeiro and Paris crashed into the Atlantic Ocean. The passenger jet stalled during a storm and plunged into the water, killing all on board. A court had previously cleared the companies in April 2023 but they were found guilty after this appeal. The Airbus A330 vanished from radars during a storm, with its wreckage found after a long search of 10,000 sq km (3,860 sq miles) of sea floor.

We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without large-scale pretraining. Keeping the architecture and optimization procedure fixed, we compare a Baseline protocol with a Modern protocol (AutoAugment/ColorJitter, CutMix, and Label Smoothing) on CIFAR-10, CIFAR-100, and Tiny-ImageNet, characterizing each attention head via Mean Attention Distance (MAD) and normalized entropy. Across all three datasets, the Modern protocol produces more local and more concentrated attention in early layers; on CIFAR-100, the minimum MAD drops from 0.316 (Baseline) to 0.008 (Modern). To identify the source of this effect, we conduct an ablation study on CIFAR-100 by adding or removing each component individually. The results identify CutMix as the determining component within our experiments: all conditions with CutMix exhibit MAD 0.024, while all conditions without CutMix remain at MAD 0.210. AutoAugment and Label Smoothing show no independent effect on locality. Taken together, these findings suggest that the pressure to classify from partial image regions, induced by CutMix, can promote the emergence of local attention in Vision Transformers.

Earlier today, Meta announced that it was testing a new Meta AI chatbot for Threads that would function a lot like Grok on X. Even though the early beta isn't available to most people on the platform yet, a number of Threads users have discovered its not possible to opt out of the feature or block chatbot's the account. While most people aren't able to interact with bot yet -- the initial testing is limited to Malaysia, Saudi Arabia, Mexico, Argentina and Singapore -- the public-facing @ meta.ai account is viewable to everyone on the platform. The account's initial post has been met with a flood of angry replies from users demanding to know why, unlike any other Threads account, there's no option to block it entirely. Some users have even said that they have reported the account for spam, which typically ends with the option to block, only to find out that the block didn't actually go into effect.