Weather forecasting is crucial for public safety, disaster prevention and mitigation, agricultural production, and energy management, with global relevance. Although deep learning has significantly advanced weather prediction, current methods face critical limitations: (i) they often struggle to capture both dynamic temporal dependencies and short-term abrupt changes, making extreme weather modeling difficult; (ii) they incur high computational costs due to extensive training and resource requirements; (iii) they have limited adaptability to multi-scale frequencies, leading to challenges when separating global trends from local fluctuations. To address these issues, we propose ClimateLLM, a foundation model for weather forecasting. It captures spatiotemporal dependencies via a cross-temporal and cross-spatial collaborative modeling framework that integrates Fourier-based frequency decomposition with Large Language Models (LLMs) to strengthen spatial and temporal modeling. Our framework uses a Mixture-of-Experts (MoE) mechanism that adaptively processes different frequency components, enabling efficient handling of both global signals and localized extreme events. In addition, we introduce a cross-temporal and cross-spatial dynamic prompting mechanism, allowing LLMs to incorporate meteorological patterns across multiple scales effectively. Extensive experiments on real-world datasets show that ClimateLLM outperforms state-of-the-art approaches in accuracy and efficiency, as a scalable solution for global weather forecasting. For almost half a century, numerical weather prediction (NWP) methods that rely on solving atmospheric partial differential equations have formed the backbone of operational forecasting Kalnay (2002); Lynch (2008); Bauer et al. (2015); Nguyen et al. (2024).

Recently, Long Chain-of-Thoughts (CoTs) have gained widespread attention for improving the reasoning capabilities of Large Language Models (LLMs). This necessitates that existing LLMs, which lack the ability to generate Long CoTs, to acquire such capability through post-training methods. Without additional training, LLMs typically enhance their mathematical reasoning abilities through inference scaling methods such as MCTS. However, they are hindered by the large action space and inefficient search strategies, making it challenging to generate Long CoTs effectively. To tackle this issue, we propose constraining the action space and guiding the emergence of Long CoTs through a refined search strategy. In our proposed Constrained Monte Carlo Tree Search (C-MCTS) framework, we limit the actions selected from a constrained action space, which is divided into five disjoint subsets: \emph{understanding}, \emph{planning}, \emph{reflection}, \emph{coding}, and \emph{summary}. Each subset is further constrained to a small number of predefined prompts, rather than allowing LLMs to generate actions arbitrarily. Additionally, we refine the search strategy by incorporating prior knowledge about the action sets, such as a human-like partial order of the action subsets and the pretrained process reward models. These strategies work together to significantly reduce the vast search space of Long CoTs. Extensive evaluations on mathematical reasoning benchmarks show that, under zero-shot settings, our method enables the 7B model to achieve reasoning capabilities that surpass those of the 72B model.

Hybrid metaheuristics are powerful techniques for solving difficult optimization problems that exploit the strengths of different approaches in a single implementation. For algorithm designers, however, creating hybrid metaheuristic implementations has become increasingly challenging due to the vast number of design options available in the literature and the fact that they often rely on their knowledge and intuition to come up with new algorithm designs. In this paper, we propose a modular metaheuristic software framework, called METAFOR, that can be coupled with an automatic algorithm configuration tool to automatically design hybrid metaheuristics. METAFOR is specifically designed to hybridize Particle Swarm Optimization, Differential Evolution and Covariance Matrix Adaptation-Evolution Strategy, and includes a local search module that allows their execution to be interleaved with a subordinate local search. We use the configuration tool irace to automatically generate 17 different metaheuristic implementations and evaluate their performance on a diverse set of continuous optimization problems. Our results show that, across all the considered problem classes, automatically generated hybrid implementations are able to outperform configured single-approach implementations, while these latter offer advantages on specific classes of functions. We provide useful insights on the type of hybridization that works best for specific problem classes, the algorithm components that contribute to the performance of the algorithms, and the advantages and disadvantages of two well-known instance separation strategies, creating stratified training set using a fix percentage and leave-one-class-out cross-validation.

Large language models (LLMs) offer powerful capabilities but come with significant environmental costs, particularly in carbon emissions. Existing studies benchmark these emissions but lack a standardized basis for comparison across models. To address this, we introduce the concept of a functional unit (FU) and develop FUEL, the first FU-based framework for evaluating LLM serving's environmental impact. Through case studies on model size, quantization, and hardware, we uncover key trade-offs in sustainability. Our findings highlight the potential for reducing carbon emissions by optimizing model selection, deployment strategies, and hardware choices, paving the way for more sustainable AI infrastructure.

A Russian drone attack badly damaged the confinement structure around the disused Chernobyl nuclear power plant intended to prevent the release of nuclear substances, a senior nuclear industry official said Friday. Ukrainian President Volodymyr Zelenskyy and the International Atomic Energy Agency had earlier reported that radiation levels remained normal at the plant, site of the world's worst nuclear accident in 1986. "The barrier, which was supposed to prevent the spread of radioactive substances, has ceased to function according to its original design," Oleksandr Tytarchuk, the plant's chief engineer, told reporters at the stricken plant.

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/.