We propose an innovative design for an all-optical Echo State Network (ESN), an advanced type of reservoir computer known for its universal computational capabilities. Our design enables fully optical implementation of arbitrary ESNs, featuring complete flexibility in optical matrix multiplication and nonlinear activation. Leveraging the nonlinear characteristics of stimulated Brillouin scattering (SBS), the architecture efficiently realizes measurement-free operations crucial for reservoir computing. The approach significantly reduces computational overhead and energy consumption compared to traditional software-based methods. Comprehensive simulations validate the system's memory capacity, nonlinear processing strength, and polynomial algebra capabilities, showcasing performance comparable to software ESNs across key benchmark tasks. Our design establishes a feasible, scalable, and universally applicable framework for optical reservoir computing, suitable for diverse machine learning applications.

Abstract--In this article, we proposed a partition-wise robust loss function (ASRL -Adapative segmented robust loss)based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the XGBoost and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the XGBoost using other loss functions. The results of multiple experiments have proven the advantages of ASRL in MSE, MAE, R2, etc. ASRL's dynamic segmentation design and adaptive threshold make it more robust and can be applied to more fields, such as as a loss function for multimodal learning and reinforcement learning, and has a large room for development.The implementation code repository github link in this paper is:ASRLCODE Index Terms--ASRL,Robustness,MSE,MAE,Loss Function I. INTRODUCTION In regression prediction of machine learning, the loss function is the core tool to measure the difference between the model prediction value and the true value. Its role runs through the entire process of model training, optimization and evaluation.

Evaluating Retrieval A ugmented G enerative Models for Document Queries in Transportation Safety C.A. Melton, A. Sorokine, S. Peterson Oak Ridge National Laboratory, Oak Ridge, TN, United States National Security Sciences Directorate ABSTRACT Applications of generative Large Language Models (LLMs) are rapidly expanding across various domains, promising significant improvements in workflow efficiency and information retrieval. However, their implementation in specialized, high - stakes domains suc h as hazardous materials transportation is challenging due to accuracy and reliability concerns. This study evaluates the performance of three fine - tuned generative models -- ChatGPT, Google's Vertex AI, and ORNL Retrieval - Augmented Generation augmented LLaMA 2 and LLaMA in retrieving regulatory information essential for hazardous material transportation compliance in the United States. Utilizing approximately 40 publicly available federal and state regulatory documents, we developed 100 realistic queries relevant to route planning and permitting requirements. Responses were qualitatively rated based on accuracy, detail, and relevance, complemented by quantitative assessments of semantic similarity between model outputs. Results demon strated that the RAG - augmented LLaMA models significantly outperformed Vertex AI and ChatGPT, providing more detailed and generally accurate information, despite occasional inconsistencies. This research introduces the first known application of RAG in tra nsportation safety, emphasizing the need for domain - specific fine - tuning and rigorous evaluation methodologies to ensure reliability and minimize the risk of inaccuracies in high - stakes environments.

How can we design AI tools that effectively support human decision-making by complementing and enhancing users' reasoning processes? Common recommendation-centric approaches face challenges such as inappropriate reliance or a lack of integration with users' decision-making processes. Here, we explore an alternative interaction model in which the AI outputs build upon users' own decision-making rationales. We compare this approach, which we call ExtendAI, with a recommendation-based AI. Participants in our mixed-methods user study interacted with both AIs as part of an investment decision-making task. We found that the AIs had different impacts, with ExtendAI integrating better into the decision-making process and people's own thinking and leading to slightly better outcomes. RecommendAI was able to provide more novel insights while requiring less cognitive effort. We discuss the implications of these and other findings along with three tensions of AI-assisted decision-making which our study revealed.

Wind direction forecasting plays a crucial role in optimizing wind energy production, but faces significant challenges due to the circular nature of directional data, error accumulation in multi-step forecasting, and complex meteorological interactions. This paper presents a novel model, WaveHiTS, which integrates wavelet transform with Neural Hierarchical Interpolation for Time Series to address these challenges. Our approach decomposes wind direction into U-V components, applies wavelet transform to capture multi-scale frequency patterns, and utilizes a hierarchical structure to model temporal dependencies at multiple scales, effectively mitigating error propagation. Experiments conducted on real-world meteorological data from Inner Mongolia, China demonstrate that WaveHiTS significantly outperforms deep learning models (RNN, LSTM, GRU), transformer-based approaches (TFT, Informer, iTransformer), and hybrid models (EMD-LSTM). The proposed model achieves RMSE values of approximately 19.2°-19.4° compared to 56°-64° for deep learning recurrent models, maintaining consistent accuracy across all forecasting steps up to 60 minutes ahead. Moreover, WaveHiTS demonstrates superior robustness with vector correlation coefficients (VCC) of 0.985-0.987 and hit rates of 88.5%-90.1%, substantially outperforming baseline models. Ablation studies confirm that each component-wavelet transform, hierarchical structure, and U-V decomposition-contributes meaningfully to overall performance. These improvements in wind direction nowcasting have significant implications for enhancing wind turbine yaw control efficiency and grid integration of wind energy.

Abstract: Automated experimentation has the potential to revolutionize scientific discovery, but its effectiveness depends on well - defined optimization targets, which are often uncertain or probabilistic in real - world settings. In this work, we demonstrate the appli cation of Multi - Objective Bayesian Optimization ( MOBO) to balance multiple, competing rewards in autonomous experimentation. Using scanning probe microscopy ( SPM) imaging, one of the most widely used and foundational SPM modes, we show that MOBO can optimize imaging parameters to enhance measurement quality, reproducibility, and efficiency. A key advantage of this approach is the ability to compute and analyze the Pareto front, which not only guides optimization but also provides physical insights into the trade - offs between different objectives. Additionally, MOBO offers a natural framework for human - in - the - loop decision - making, enabling researchers to fine - tune ex perimental trade - offs based on domain expertise. By standardizing high - quality, reproducible measurements and integrating human input into AI - driven optimization, this work highlights MOBO as a powerful tool for advancing autonomous scientific discovery. I. Introduction Automated scientific discovery is rapidly emerging as a transformative research paradigm, reshaping experimental methodologies through the integration of automated instrumentation, AI - driven decision - making, and multi - tool workflows [1, 2] . By enabling autonomous hypothesis testing, adaptive experimentation, and real - time optimization, these systems have the potential to significantly accelerate discoveries across various scientific domains [18 - 21] . A fundamental requirement for active discovery workflows is the definition of optimization targets or reward functions that drive the iterative learning process [18] . These reward functions form the foundation of autonomous workflows, guiding experimental decisions and facilitating interoperability among multiple tools in complex research environments.

Fleets of robo-taxis offering on-demand transportation services, commonly known as Autonomous Mobility-on-Demand (AMoD) systems, hold significant promise for societal benefits, such as reducing pollution, energy consumption, and urban congestion. However, orchestrating these systems at scale remains a critical challenge, with existing coordination algorithms often failing to exploit the systems' full potential. This work introduces a novel decision-making framework that unites mathematical modeling with data-driven techniques. In particular, we present the AMoD coordination problem through the lens of reinforcement learning and propose a graph network-based framework that exploits the main strengths of graph representation learning, reinforcement learning, and classical operations research tools. Extensive evaluations across diverse simulation fidelities and scenarios demonstrate the flexibility of our approach, achieving superior system performance, computational efficiency, and generalizability compared to prior methods. Finally, motivated by the need to democratize research efforts in this area, we release publicly available benchmarks, datasets, and simulators for network-level coordination alongside an open-source codebase designed to provide accessible simulation platforms and establish a standardized validation process for comparing methodologies. Code available at: https://github.com/StanfordASL/RL4AMOD

-- Digital twins for power electronics require accurate power losses whose direct measurements are often impractical or impossible in real-world applications. This paper presents a novel hybrid framework that combines physics-based thermal modeling with data-driven techniques to identify and correct power losses accurately using only temperature measurements. Our approach leverages a cascaded architecture where a neural network learns to correct the outputs of a nominal power loss model by backpropagating through a reduced-order thermal model. We explore two neural architectures, a bootstrapped feedforward network, and a recurrent neural network, demonstrating that the bootstrapped feedforward approach achieves superior performance while maintaining computational efficiency for real-time applications. Between the interconnection, we included normalization strategies and physics-guided training loss functions to preserve stability and ensure physical consistency. Experimental results show that our hybrid model reduces both temperature estimation errors (from 7.2 6.8 C to 0.3 0.3 C) and power loss prediction errors (from 5.4 6.6W to 0.2 0.3W) compared to traditional physics-based approaches, even in the presence of thermal model uncertainties. This methodology allows us to accurately estimate power losses without direct measurements, making it particularly helpful for real-time industrial applications where sensor placement is hindered by cost and physical limitations. This paper has been accepted for presentation at the 23rd IEEE European Control Conference 2025 IEEE. Thermal management and sensing play a critical role in many industrial applications that rely on power electronics.

On Tuesday, President Donald Trump held a press conference to announce the signing of executive orders intended to shape American energy policy in favor of one particular source: coal, the most carbon-intense fossil fuel. "I call it beautiful, clean coal," President Trump said while flanked by a crowd of miners at the White House. "I tell my people never use the word coal, unless you put'beautiful, clean' before it." Trump has talked about saving coal, and coal jobs, for as long as he's been in politics. This time, he's got a convenient vehicle for his policies: the growth of AI and data centers, which could potentially supercharge American energy demand over the coming years.

The EU has revealed details of a 20bn ( 17bn) plan to create new sites equipped with vast supercomputers in Europe to develop the next generation of artificial intelligence models, while opening the door to amending its landmark law that regulates the technology. Publishing a strategy to turn Europe into an "AI continent", the European Commission vice-president Henna Virkkunen said the technology was at the heart of making Europe more competitive, secure and technologically sovereign, adding: "The global race for AI is far from over." The EU is attempting to catch up with the US and China, which have taken a lead in pioneering the technology that increasingly powers shopping websites and self-driving cars, generates text, and is predicted to play a transformative role in healthcare, security and defence, and advanced manufacturing, among other sectors. The US has a commanding lead in AI, far ahead of China. A report from Stanford University this week said 40 "notable AI models" – meaning influential – were produced by institutions in the US in 2024, compared with 15 in China and three in Europe (all French).