The escalating challenges of managing vast sensor-generated data, particularly in audio applications, necessitate innovative solutions. Current systems face significant computational and storage demands, especially in real-time applications like gunshot detection systems (GSDS), and the proliferation of edge sensors exacerbates these issues. This paper proposes a groundbreaking approach with a near-sensor model tailored for intelligent audio-sensing frameworks. Utilizing a Fast Fourier Transform (FFT) module, convolutional neural network (CNN) layers, and HyperDimensional Computing (HDC), our model excels in low-energy, rapid inference, and online learning. It is highly adaptable for efficient ASIC design implementation, offering superior energy efficiency compared to conventional embedded CPUs or GPUs, and is compatible with the trend of shrinking microphone sensor sizes. Comprehensive evaluations at both software and hardware levels underscore the model's efficacy. Software assessments through detailed ROC curve analysis revealed a delicate balance between energy conservation and quality loss, achieving up to 82.1% energy savings with only 1.39% quality loss. Hardware evaluations highlight the model's commendable energy efficiency when implemented via ASIC design, especially with the Google Edge TPU, showcasing its superiority over prevalent embedded CPUs and GPUs.

A common strategy for fact-checking long-form content generated by Large Language Models (LLMs) is extracting simple claims that can be verified independently. Since inaccurate or incomplete claims compromise fact-checking results, ensuring claim quality is critical. However, the lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. To address this gap, we propose a framework for evaluating claim extraction in the context of fact-checking along with automated, scalable, and replicable methods for applying this framework, including novel approaches for measuring coverage and decontextualization. We also introduce Claimify, an LLM-based claim extraction method, and demonstrate that it outperforms existing methods under our evaluation framework. A key feature of Claimify is its ability to handle ambiguity and extract claims only when there is high confidence in the correct interpretation of the source text.

Large language models (LLMs) are revolutionizing many science and engineering fields. However, their huge model sizes impose extremely demanding needs of computational resources in the pre-training stage. Although low-rank factorizations can reduce model parameters, their direct application in LLM pre-training often lead to non-negligible performance loss. To address this fundamental challenge, we introduce CoLA and its memory-efficient implementation, CoLA-M. We leverage the low-rank structure observed widely in model activations, enforcing non-linear transformations between factorized weight matrices to reduce model size, boost model capacity and training efficiency. Experiments on LLaMA models with 60 million to 7 billion parameters show that CoLA reduces the computing cost by $\bf 2\pmb{\times}$ and improves training throughput by $\bf 1.86\pmb{\times}$ while maintaining full-rank level performance. CoLA-M further squeezes memory cost without sacrificing throughput, offering a pre-training approach with collectively superior parameter, computing, and memory efficiency. The LLMs produced are also $\bf 2\pmb{\times}$ smaller, enabling faster inference with lower memory cost on resource-constrained platforms

We present a method leveraging extreme learning machine (ELM) type randomized neural networks (NNs) for learning the exact time integration algorithm for initial value problems (IVPs). The exact time integration algorithm for non-autonomous systems can be represented by an algorithmic function in higher dimensions, which satisfies an associated system of partial differential equations with corresponding boundary conditions. Our method learns the algorithmic function by solving this associated system using ELM with a physics informed approach. The trained ELM network serves as the learned algorithm and can be used to solve the IVP with arbitrary initial data or step sizes from some domain. When the right hand side of the non-autonomous system exhibits a periodicity with respect to any of its arguments, while the solution itself to the problem is not periodic, we show that the algorithmic function is either periodic, or when it is not, satisfies a well-defined relation for different periods. This property can greatly simplify the algorithm learning in many problems. We consider explicit and implicit NN formulations, leading to explicit or implicit time integration algorithms, and discuss how to train the ELM network by the nonlinear least squares method. Extensive numerical experiments with benchmark problems, including non-stiff, stiff and chaotic systems, show that the learned NN algorithm produces highly accurate solutions in long-time simulations, with its time-marching errors decreasing nearly exponentially with increasing degrees of freedom in the neural network. We compare extensively the computational performance (accuracy vs.~cost) between the current NN algorithm and the leading traditional time integration algorithms. The learned NN algorithm is computationally competitive, markedly outperforming the traditional algorithms in many problems.

Legged locomotion is not just about mobility; it also encompasses crucial objectives such as energy efficiency, safety, and user experience, which are vital for real-world applications. However, key factors such as battery power consumption and stepping noise are often inaccurately modeled or missing in common simulators, leaving these aspects poorly optimized or unaddressed by current sim-to-real methods. Hand-designed proxies, such as mechanical power and foot contact forces, have been used to address these challenges but are often problem-specific and inaccurate. In this paper, we propose a data-driven framework for fine-tuning locomotion policies, targeting these hard-to-simulate objectives. Our framework leverages real-world data to model these objectives and incorporates the learned model into simulation for policy improvement. We demonstrate the effectiveness of our framework on power saving for quadruped locomotion, achieving a significant 24-28\% net reduction in total power consumption from the battery pack at various speeds. In essence, our approach offers a versatile solution for optimizing hard-to-simulate objectives in quadruped locomotion, providing an easy-to-adapt paradigm for continual improving with real-world knowledge. Project page https://hard-to-sim.github.io/.

A Russian drone with a high-explosive warhead has hit the Chornobyl nuclear power plant in the Kyiv region, Ukraine said, amid warnings by the military that Russia launched 133 unmanned vehicles against the country. Ukrainian President Volodymyr Zelenskyy said on Friday that the drone strike significantly damaged the protective containment shelter and started a fire, which has been put out. The Kremlin responded saying Russia does not hit nuclear sites. Radiation levels at the site have not increased, according to Zelenskyy and the International Atomic Energy Agency (IAEA). The IAEA did not attribute blame but said the drone strike occurred at 01:50am local time (23:50 GMT) and that there was "no indication of a breach in the … inner containment" shell, a protective cover built around the fourth reactor of the plant.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. An alleged drone struck the protective shell covering the Chernobyl Nuclear Power Plant in Ukraine early Friday, and Ukrainian President Volodymyr Zelenskyy is pointing the finger at Russia. The International Atomic Energy Agency reported on X that overnight Thursday, the IAEA team at the Chornobyl site heard an explosion coming from the New Safe Confinement. The site protects the remains of the nuclear reactor that exploded in Chernobyl in 1986 and was reportedly set ablaze after an unmanned aerial vehicle (UAV) struck the NSC roof.

Ukrainian President Volodymyr Zelenskyy said a Russian drone attack caused a fire at the site of the former Chernobyl nuclear power plant in Ukraine. The UN's nuclear watchdog said radiation levels were normal following the fire.

Ukrainian President Volodymyr Zelenskyy said Friday that a Russian drone had struck a cover built to contain radiation at the Chernobyl nuclear power plant, adding that "radiation levels have not increased." The Ukrainian air force said that Russia had launched more than 100 drones across the country overnight -- including attack drones -- targeting northern regions of the country where the Chernobyl power plant lies. "Last night, a Russian attack drone with a high-explosive warhead struck the cover protecting the world from radiation at the destroyed 4th power unit of the Chernobyl Nuclear Power Plant," Zelenskyy said in a social media post. The International Atomic Energy Agency also reported an "explosion" at the site, and said "radiation levels inside and outside remain normal and stable." The agency, which has had a team deployed on the site since the early stages of Russia's invasion of Ukraine, published images apparently showing the drone on fire after crashing into the covering.

The IAEA, which monitors nuclear safety the world, said radiation levels inside and outside Chernobyl remain normal and stable. The agency remains on "high alert" after the incident, with its director general Rafael Mariano Grossi saying there is "no room for complacency". Chernobyl is the site of the world's worst nuclear accident - a catastrophic explosion that sent a plume of radioactive material into the air in 1986, triggering a public health emergency across Europe. Zelensky posted footage on X appearing to show damage to the giant shield, made of concrete and steel, which covers the remains of the reactor that lost its roof in the explosion. The shield is designed to prevent further radioactive material leaking out over the next century.