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).

3D semantic segmentation plays a critical role in urban modelling, enabling detailed understanding and mapping of city environments. In this paper, we introduce Turin3D: a new aerial LiDAR dataset for point cloud semantic segmentation covering an area of around 1.43 km2 in the city centre of Turin with almost 70M points. We describe the data collection process and compare Turin3D with others previously proposed in the literature. We did not fully annotate the dataset due to the complexity and time-consuming nature of the process; however, a manual annotation process was performed on the validation and test sets, to enable a reliable evaluation of the proposed techniques. We first benchmark the performances of several point cloud semantic segmentation models, trained on the existing datasets, when tested on Turin3D, and then improve their performances by applying a semi-supervised learning technique leveraging the unlabelled training set. The dataset will be publicly available to support research in outdoor point cloud segmentation, with particular relevance for self-supervised and semi-supervised learning approaches given the absence of ground truth annotations for the training set.

Probabilistic QoS Metric Forecasting in Delay-T olerant Networks Using Conditional Diffusion Models on Latent Dynamics Enming Zhang School of Computer Science Nanjing University of Posts and T elecommunications Nanjing, China b20060123@njupt.edu.cn Zheng Liu School of Computer Science Nanjing University of Posts and T elecommunications Nanjing, China zliu@njupt.edu.cn Y u Xiang School of Computer Science Nanjing University of Posts and T elecommunications Nanjing, China 1221045920@njupt.edu.cn Abstract --Active QoS metric prediction, commonly employed in the maintenance and operation of DTN, could enhance network performance regarding latency, throughput, energy consumption, and dependability. Naturally formulated as a multivariate time series forecasting problem, it attracts substantial research efforts. Traditional mean regression methods for time series forecasting cannot capture the data complexity adequately, resulting in deteriorated performance in operational tasks in DTNs such as routing. This paper formulates the prediction of QoS metrics in DTN as a probabilistic forecasting problem on multivariate time series, where one could quantify the uncertainty of forecasts by characterizing the distribution of these samples. The proposed approach hires diffusion models and incorporates the latent temporal dynamics of non-stationary and multi-mode data into them.

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, including sentiment analysis. However, data quality--particularly when sourced from social media--can significantly impact their accuracy. This research explores how textual nuances, including emojis and sarcasm, affect sentiment analysis, with a particular focus on improving data quality through text paraphrasing techniques. To address the lack of labeled sarcasm data, the authors created a human-labeled dataset of 5929 tweets that enabled the assessment of LLM in various sarcasm contexts. The results show that when topic-specific datasets, such as those related to nuclear power, are used to finetune LLMs these models are not able to comprehend accurate sentiment in presence of sarcasm due to less diverse text, requiring external interventions like sarcasm removal to boost model accuracy. Sarcasm removal led to up to 21% improvement in sentiment accuracy, as LLMs trained on nuclear power-related content struggled with sarcastic tweets, achieving only 30% accuracy. In contrast, LLMs trained on general tweet datasets, covering a broader range of topics, showed considerable improvements in predicting sentiment for sarcastic tweets (60% accuracy), indicating that incorporating general text data can enhance sarcasm detection. The study also utilized adversarial text augmentation, showing that creating synthetic text variants by making minor changes significantly increased model robustness and accuracy for sarcastic tweets (approximately 85%). Additionally, text paraphrasing of tweets with fragmented language transformed around 40% of the tweets with low-confidence labels into high-confidence ones, improving LLMs sentiment analysis accuracy by 6%.

LLM training is scaled up to 10Ks of GPUs by a mix of data-(DP) and model-parallel (MP) execution. Critical to achieving efficiency is tensor-parallel (TP; a form of MP) execution within tightly-coupled subsets of GPUs, referred to as a scale-up domain, and the larger the scale-up domain the better the performance. New datacenter architectures are emerging with more GPUs able to be tightly-coupled in a scale-up domain, such as moving from 8 GPUs to 72 GPUs connected via NVLink. Unfortunately, larger scale-up domains increase the blast-radius of failures, with a failure of single GPU potentially impacting TP execution on the full scale-up domain, which can degrade overall LLM training throughput dramatically. With as few as 0.1% of GPUs being in a failed state, a high TP-degree job can experience nearly 10% reduction in LLM training throughput. We propose nonuniform-tensor-parallelism (NTP) to mitigate this amplified impact of GPU failures. In NTP, a DP replica that experiences GPU failures operates at a reduced TP degree, contributing throughput equal to the percentage of still-functional GPUs. We also propose a rack-design with improved electrical and thermal capabilities in order to sustain power-boosting of scale-up domains that have experienced failures; combined with NTP, this can allow the DP replica with the reduced TP degree (i.e., with failed GPUs) to keep up with the others, thereby achieving near-zero throughput loss for large-scale LLM training.