No part of the globe is free of human fingerprints. Should we deploy technology to change it back? When people talk about "nature," they're generally talking about things that aren't made by human beings. But while there is plenty of God's creation to go around, it is hard to think of anything on Earth that human hands haven't affected. In the Brazilian rainforest, scientists have found microplastics in the bellies of animals ranging from red howler monkeys to manatees. In remotest Yakutia, where much of the earth remains untrodden by human feet, the carbon in the sky above melts the permafrost below.

Optimal transport (OT) [30, 25] has become increasingly popular in the machine learning and optimizationcommunity.

Takeda's psoriasis pill developed with AI assistance succeeds in trials Psoriasis is a chronic autoimmune disorder that causes rashes marked by itchy, scaly rashes and afflicts more than 125 million people worldwide. Takeda Pharmaceutical announced that its oral psoriasis drug zasocitinib proved safe and effective in late-stage trials, marking a milestone in its effort to treat the incurable skin condition and offset looming revenue pressure. Patients with moderate-to-severe plaque psoriasis who took the once-daily pill showed significantly clearer skin compared with those on placebo or the existing therapy apremilast, the company said in a statement Thursday. Takeda plans to submit data to the U.S. Food and Drug Administration and other regulators beginning in fiscal year 2026. If approved, zasocitinib would join the small but growing oral psoriasis treatments -- long a market dominated by ointments and injectable antibody therapies -- and stand out as one of the first drugs discovered with the help of artificial intelligence.

Given a basis space (e.g., pixel grid) and a transportation cost function (e.g.,

Is Trump losing patience with Putin? Will sanctions against Russian oil giants hurt Putin? Russian and Ukrainian troops have fought battles in the ruins of Pokrovsk, a transport and logistics hub in eastern Ukraine, with Ukraine's military reporting fierce fighting under way in a part of the city that was key for Kyiv's front-line logistics. Ukrainian President Volodymyr Zelenskyy said he visited troops fighting near the eastern city of Dobropillia, where Ukrainian forces are conducting a counteroffensive against Russian troops. Russia struck civilian energy and port infrastructure in a massive overnight drone attack on Ukraine's southern region of Odesa, the region's governor said in a post on the Telegram messaging app, adding that rescuers extinguished fires and there were no casualties.

Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. This has led to the development of separate thinking and non-thinking LLM variants, leaving the onus of selecting the optimal model for each query on the end user. We introduce OptimalThinkingBench, a unified benchmark that jointly evaluates overthinking and underthinking in LLMs and also encourages the development of optimally-thinking models that balance performance and efficiency. Our benchmark comprises two sub-benchmarks: OverthinkingBench, featuring simple math and general queries in 72 domains, and UnderthinkingBench, containing 11 challenging reasoning tasks along with harder math problems. Using novel thinking-adjusted accuracy metrics, we extensively evaluate 33 different thinking and non-thinking models and show that no model is able to optimally think on our benchmark. Thinking models often overthink for hundreds of tokens on the simplest user queries without improving performance. In contrast, large non-thinking models underthink, often falling short of much smaller thinking models. We further explore several methods to encourage optimal thinking, but find that these approaches often improve on one sub-benchmark at the expense of the other, highlighting the need for better unified and optimal models in the future.

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including spontaneous speech, environmental noise, and severely constrained datasets from under-documented languages. In this paper, we benchmark the performance of two fine-tuned multilingual ASR models, MMS and XLS-R, on five typologically diverse low-resource languages with control of training data duration. Our findings show that MMS is best suited when extremely small amounts of training data are available, whereas XLS-R shows parity performance once training data exceed one hour. We provide linguistically grounded analysis for further provide insights towards practical guidelines for field linguists, highlighting reproducible ASR adaptation approaches to mitigate the transcription bottleneck in language documentation.

Chenghua Lu received the B.S. degree in Mechanical Engineering from Northeastern University, Shenyang, China, in 2017, and the M.S. degree in Mechanical Manufacturing and Automation from the University of Chinese Academy of Sciences, Beijing, China, in 2021. She is currently working toward the Ph.D. degree majoring in Engineering Mathematics with the School of Mathematics Engineering and Technology and Bristol Robotics Laboratory, University of Bristol, Bristol, UK. Her research interests include tactile sensing and soft robotics. Kailuan T ang received a B.S. degree in Communication Engineering from the Southern University of Science and Technology (SUSTech), Shenzhen, China in 2017. He is currently working towards a Ph.D. degree majoring in Mechanics with the School of Mechatronics Engineering, Harbin Institute of Technology.

Fault detection in rotating machinery is a complex task, particularly in small and heterogeneous dataset scenarios. Variability in sensor placement, machinery configurations, and structural differences further increase the complexity of the problem. Conventional deep learning approaches often demand large, homogeneous datasets, limiting their applicability in data-scarce industrial environments. While transfer learning and few-shot learning have shown potential, however, they are often constrained by the need for extensive fault datasets. This research introduces a unified framework leveraging a novel progressive neural network (PNN) architecture designed to address these challenges. The PNN sequentially estimates the fixed-size refined features of the higher order with the help of all previously estimated features and appends them to the feature set. This fixed-size feature output at each layer controls the complexity of the PNN and makes it suitable for effective learning from small datasets. The framework's effectiveness is validated on eight datasets, including six open-source datasets, one in-house fault simulator, and one real-world industrial dataset. The PNN achieves state-of-the-art performance in fault detection across varying dataset sizes and machinery types, highlighting superior generalization and classification capabilities.