Bayesian Additive Regression Trees [BART, Chipman et al., 2010] have gained significant popularity due to their remarkable predictive performance and ability to quantify uncertainty. However, standard decision tree models rely on recursive data splits at each decision node, using deterministic decision rules based on a single univariate feature. This approach limits their ability to effectively capture complex decision boundaries, particularly in scenarios involving multiple features, such as spatial domains, or when transitions are either sharp or smoothly varying. In this paper, we introduce a novel probabilistic additive decision tree model that employs a soft split rule. This method enables highly flexible splits that leverage both univariate and multivariate features, while also respecting the geometric properties of the feature domain. Notably, the probabilistic split rule adapts dynamically across decision nodes, allowing the model to account for varying levels of smoothness in the regression function. We demonstrate the utility of the proposed model through comparisons with existing tree-based models on synthetic datasets and a New York City education dataset.

HRA (Human Reliability Analysis) data is crucial for advancing HRA methodologies. however, existing data collection methods lack the necessary granularity, and most approaches fail to capture dynamic features. Additionally, many methods require expert knowledge as input, making them time-consuming and labor-intensive. To address these challenges, we propose a new paradigm for the automated collection of HRA data. Our approach focuses on key indicators behind human error, specifically measuring workload in collaborative settings. This study introduces a novel, scenario-driven method for workload estimation, leveraging fine-tuned large language models (LLMs). By training LLMs on real-world operational data from high-temperature gas-cooled reactors (HTGRs), we simulate human behavior and cognitive load in real time across various collaborative scenarios. The method dynamically adapts to changes in operator workload, providing more accurate, flexible, and scalable workload estimates. The results demonstrate that the proposed WELLA (Workload Estimation with LLMs and Agents) outperforms existing commercial LLM-based methods in terms of prediction accuracy.

Advancements in Natural Language Processing are heavily reliant on the Transformer architecture, whose improvements come at substantial resource costs due to ever-growing model sizes. This study explores optimization techniques, including Quantization, Knowledge Distillation, and Pruning, focusing on energy and computational efficiency while retaining performance. Among standalone methods, 4-bit Quantization significantly reduces energy use with minimal accuracy loss. Hybrid approaches, like NVIDIA's Minitron approach combining KD and Structured Pruning, further demonstrate promising trade-offs between size reduction and accuracy retention. A novel optimization equation is introduced, offering a flexible framework for comparing various methods. Through the investigation of these compression methods, we provide valuable insights for developing more sustainable and efficient LLMs, shining a light on the often-ignored concern of energy efficiency.

Lifecycle management of power converters continues to thrive with emerging artificial intelligence (AI) solutions, yet AI mathematical explainability remains unexplored in power electronics (PE) community. The lack of theoretical rigor challenges adoption in mission-critical applications. Therefore, this letter proposes a generic framework to evaluate mathematical explainability, highlighting inference stability and training convergence from a Lipschitz continuity perspective. Inference stability governs consistent outputs under input perturbations, essential for robust real-time control and fault diagnosis. Training convergence guarantees stable learning dynamics, facilitating accurate modeling in PE contexts. Additionally, a Lipschitz-aware learning rate selection strategy is introduced to accelerate convergence while mitigating overshoots and oscillations. The feasibility of the proposed Lipschitz-oriented framework is demonstrated by validating the mathematical explainability of a state-of-the-art physics-in-architecture neural network, and substantiated through empirical case studies on dual-active-bridge converters. This letter serves as a clarion call for the PE community to embrace mathematical explainability, heralding a transformative era of trustworthy and explainable AI solutions that potentially redefine the future of power electronics.

Searching for the Extreme Operating Conditions (EOCs) is one of the core problems of power system relay protection setting calculation. The current methods based on brute-force search, heuristic algorithms, and mathematical programming can hardly meet the requirements of today's power systems in terms of computation speed due to the drastic changes in operating conditions induced by renewables and power electronics. This paper proposes an EOC fast search method, named Graph Dueling Double Deep Q Network (Graph D3QN), which combines graph neural network and deep reinforcement learning to address this challenge. First, the EOC search problem is modeled as a Markov decision process, where the information of the underlying power system is extracted using graph neural networks, so that the EOC of the system can be found via deep reinforcement learning. Then, a two-stage Guided Learning and Free Exploration (GLFE) training framework is constructed to accelerate the convergence speed of reinforcement learning. Finally, the proposed Graph D3QN method is validated through case studies of searching maximum fault current for relay protection setting calculation on the IEEE 39-bus and 118-bus systems. The experimental results demonstrate that Graph D3QN can reduce the computation time by 10 to 1000 times while guaranteeing the accuracy of the selected EOCs.

The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks. This work analyzes existing VLM evaluation techniques, including automated metrics, AIbased assessments, and human evaluations across diverse tasks. We first introduce Robin - a novel suite of VLMs that we built by combining Large Language Models (LLMs) and Vision Encoders (VEs) at multiple scales, and use Robin to identify shortcomings of current evaluation approaches across scales. Next, to overcome the identified limitations, we introduce CHIRP - a new long form response benchmark we developed for more robust and complete VLM evaluation. We provide open access to the Robin training code, model suite, and CHIRP benchmark to promote reproducibility and advance VLM research. Recently, a lot of significant advances have been made in Vision-Language Models (VLMs), driven by breakthroughs in computer vision and natural language processing Chen et al. (2022); Li et al. (2023b); Liu et al. (2023b); Sun et al. (2023). However, existing VLM benchmarks, often designed for specific tasks (e.g., VQAv2 Goyal et al. (2017)), struggle to accurately reflect real-world VLM performance and capture nuanced differences between models Hsieh et al. (2024). This is particularly evident when evaluating models with significant architectural variations, where standard benchmark scores remain similar despite noticeable differences in human-perceived model quality. To address this issue, we introduce CHIRP, a hybrid VLM benchmark that combines automated metrics' scalability with human evaluators' nuanced judgment. We argue that this approach is crucial for capturing the complexities of VLM behavior, which traditional benchmarks often fail to represent. To demonstrate the limitations of existing benchmarks and the efficacy of our proposed method, we introduce Robin, a suite of VLMs trained at various scales, inspired by the Pythia language model suite Biderman et al. (2023). By systematically varying the Vision Encoder (VE) and the Large Language Model (LLM) sizes, we will show that while benchmark scores remain largely unaffected, human evaluations reveal significant differences in the models' outputs quality. Our findings underscore the need for more robust and human-centric VLM evaluation methodologies. CHIRP paves the way for developing more reliable and informative VLM benchmarks, ultimately leading to the creation of more effective and impactful VLMs. Our Contributions: We investigate the drawbacks of relying on automatic metrics and show the benefits of AI-based and human-based evaluations of VLMs. We train and release an open-source collection of VLMs named Robin. Robin is a scaling suite based on LLMs and VEs of different sizes.

Within the rapidly evolving domain of Electronic Design Automation (EDA), Large Language Models (LLMs) have emerged as transformative technologies, offering unprecedented capabilities for optimizing and automating various aspects of electronic design. This survey provides a comprehensive exploration of LLM applications in EDA, focusing on advancements in model architectures, the implications of varying model sizes, and innovative customization techniques that enable tailored analytical insights. By examining the intersection of LLM capabilities and EDA requirements, the paper highlights the significant impact these models have on extracting nuanced understandings from complex datasets. Furthermore, it addresses the challenges and opportunities in integrating LLMs into EDA workflows, paving the way for future research and application in this dynamic field. Through this detailed analysis, the survey aims to offer valuable insights to professionals in the EDA industry, AI researchers, and anyone interested in the convergence of advanced AI technologies and electronic design.

Optimization problems in process engineering, including design and operation, can often pose challenges to many solvers: multi-modal, non-smooth, and discontinuous models often with large computational requirements. In such cases, the optimization problem is often treated as a black box in which only the value of the objective function is required, sometimes with some indication of the measure of the violation of the constraints. Such problems have traditionally been tackled through the use of direct search and meta-heuristic methods. The challenge, then, is to determine which of these methods or combination of methods should be considered to make most effective use of finite computational resources. This paper presents a multi-agent system for optimization which enables a set of solvers to be applied simultaneously to an optimization problem, including different instantiations of any solver. The evaluation of the optimization problem model is controlled by a scheduler agent which facilitates cooperation and competition between optimization methods. The architecture and implementation of the agent system is described in detail, including the solver, model evaluation, and scheduler agents. A suite of direct search and meta-heuristic methods has been developed for use with this system. Case studies from process systems engineering applications are presented and the results show the potential benefits of automated cooperation between different optimization solvers and motivates the implementation of competition between solvers.

The prediction of solar irradiance enhances reliability in photovoltaic (PV) solar plant generation and grid integration. In Colombia, PV plants face penalties if energy production deviates beyond governmental thresholds from intraday market offers. This research employs Long Short-Term Memory (LSTM) and Bidirectional-LSTM (Bi-LSTM) models, utilizing meteorological data from a PV plant in El Paso, Cesar, Colombia, to predict solar irradiance with a 6-hour horizon and 10-minute resolution. While Bi-LSTM showed superior performance, the LSTM model achieved comparable results with significantly reduced training time (6 hours versus 18 hours), making it computationally advantageous. The LSTM predictions were averaged to create an hourly resolution model, evaluated using Mean Absolute Error, Root-Mean-Square Error, Normalized Root-Mean-Square Error, and Mean Absolute Percentage Error metrics. Comparison with the Global Forecast System (GFS) revealed similar performance, with both models effectively capturing daily solar irradiance patterns. The forecast model integrates with an Object-Oriented power production model, enabling accurate energy offers in the intraday market while minimizing penalty costs.

--Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. T o tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Data-driven fault diagnosis techniques have gained significant prominence over the past two decades [1-5]. However, most of them necessitate sufficient training data to achieve reliable modeling performance[6-9]. Unfortunately, fault data is typically limited in comparison to normal data. This is because engineering equipment primarily operates under normal conditions, and the probabilities of faults vary across different working environments. Besides, fault simulation experiments are costly and inevitably deviate to some extent from real industrial environments. These possible reasons consequently contribute to class imbalance and a long-tailed distribution among different conditions [10]. The performance of the model typically suffers as it tends to prioritize the normal class, consequently neglecting fault classes or tail classes.