Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation variations. Despite the existence of various speech recognition datasets, none of them has provided a fine-grained classification of the 63 dialects specific to individual provinces of Vietnam. To address this gap, we introduce Vietnamese Multi-Dialect (ViMD) dataset, a novel comprehensive dataset capturing the rich diversity of 63 provincial dialects spoken across Vietnam. Our dataset comprises 102.56 hours of audio, consisting of approximately 19,000 utterances, and the associated transcripts contain over 1.2 million words. To provide benchmarks and simultaneously demonstrate the challenges of our dataset, we fine-tune state-of-the-art pre-trained models for two downstream tasks: (1) Dialect identification and (2) Speech recognition. The empirical results suggest two implications including the influence of geographical factors on dialects, and the constraints of current approaches in speech recognition tasks involving multi-dialect speech data. Our dataset is available for research purposes.

We employ Large language models (LLMs) such as GPT-fine-tuning on the LLaMa-2, Mixtral 8 7B, 4 (OpenAI, 2023), BLOOM (Le Scao et al, Gemma, and conduct a comprehensive evaluation 2023), LLaMa-2 (Touvron et al, 2023), Mistral of Vietnamese LLMs across various scenarios and (Jiang et al., 2023), Mixtral (Jiang et al., 2024), settings. Throughout the thorough evaluation process, Gemma (Team et al., 2024) have made significant we observe the following: (i) larger language contributions to the field of natural language processing models exhibit unseen capabilities compared to (NLP). Despite their advancements, a gap smaller counterparts; (ii) larger language models remains in their specialization for many languages, tend to manifest more biases, produce uncalibrated including Vietnamese. This paper addresses the results, and are more susceptible to the influence development and evaluation of Vietnamese-centric of input prompts; (iii) the quality of training or LLMs. Vietnam, with a population surpassing 100 fine-tuning datasets is the key for unlocking LLM million, ranks as the 16th most populous country performance. Our key contributions include: globally.

In recent years, the field of data-driven neural network-based machine learning (ML) algorithms has grown significantly and spurred research in its applicability to instrumentation and control systems. While they are promising in operational contexts, the trustworthiness of such algorithms is not adequately assessed. Failures of ML-integrated systems are poorly understood; the lack of comprehensive risk modeling can degrade the trustworthiness of these systems. In recent reports by the National Institute for Standards and Technology, trustworthiness in ML is a critical barrier to adoption and will play a vital role in intelligent systems' safe and accountable operation. Thus, in this work, we demonstrate a real-time model-agnostic method to evaluate the relative reliability of ML predictions by incorporating out-of-distribution detection on the training dataset. It is well documented that ML algorithms excel at interpolation (or near-interpolation) tasks but significantly degrade at extrapolation. This occurs when new samples are "far" from training samples. The method, referred to as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets, which is used to calculate a prediction's relative reliability. LADDR is demonstrated on a feedforward neural network-based model used to predict safety significant factors during different loss-of-flow transients. LADDR is intended as a "data supervisor" and determines the appropriateness of well-trained ML models in the context of operational conditions. Ultimately, LADDR illustrates how training data can be used as evidence to support the trustworthiness of ML predictions when utilized for conventional interpolation tasks.

Given harsh operating conditions and physical constraints in reactors, nuclear applications cannot afford to equip the physical asset with a large array of sensors. Therefore, it is crucial to carefully determine the placement of sensors within the given spatial limitations, enabling the reconstruction of reactor flow fields and the creation of nuclear digital twins. Various design considerations are imposed, such as predetermined sensor locations, restricted areas within the reactor, a fixed number of sensors allocated to a specific region, or sensors positioned at a designated distance from one another. We develop a data-driven technique that integrates constraints into an optimization procedure for sensor placement, aiming to minimize reconstruction errors. Our approach employs a greedy algorithm that can optimize sensor locations on a grid, adhering to user-defined constraints. We demonstrate the near optimality of our algorithm by computing all possible configurations for selecting a certain number of sensors for a randomly generated state space system. In this work, the algorithm is demonstrated on the Out-of-Pile Testing and Instrumentation Transient Water Irradiation System (OPTI-TWIST) prototype vessel, which is electrically heated to mimic the neutronics effect of the Transient Reactor Test facility (TREAT) at Idaho National Laboratory (INL). The resulting sensor-based reconstruction of temperature within the OPTI-TWIST minimizes error, provides probabilistic bounds for noise-induced uncertainty and will finally be used for communication between the digital twin and experimental facility.

Huyen, aka Huyen Chip, ranked fifth in the annual Top Voices list released this week by the U.S. professional networking site. It compiles the list by examining all sharing activity on its platform from October 1, 2019 through September 30, 2020, and using a combination of quantitative and qualitative signals including engagement (comments, reactions and shares), follower growth and posting cadence. It said: "Having worked at prominent tech companies including Netflix and NVIDIA, Huyen joined the AI startup Snorkel last December. A Stanford graduate, Huyen turned to LinkedIn to find reviewers for the course she'll start teaching there in January next year, Machine Learning Systems Design." Before coming to the U.S., Chip helped launch Vietnam's second most popular web browser, Coc Coc.

In nuclear engineering, modeling and simulations (M&Ss) are widely applied to support risk-informed safety analysis. Since nuclear safety analysis has important implications, a convincing validation process is needed to assess simulation adequacy, i.e., the degree to which M&S tools can adequately represent the system quantities of interest. However, due to data gaps, validation becomes a decision-making process under uncertainties. Expert knowledge and judgments are required to collect, choose, characterize, and integrate evidence toward the final adequacy decision. However, in validation frameworks CSAU: Code Scaling, Applicability, and Uncertainty (NUREG/CR-5249) and EMDAP: Evaluation Model Development and Assessment Process (RG 1.203), such a decision-making process is largely implicit and obscure. When scenarios are complex, knowledge biases and unreliable judgments can be overlooked, which could increase uncertainty in the simulation adequacy result and the corresponding risks. Therefore, a framework is required to formalize the decision-making process for simulation adequacy in a practical, transparent, and consistent manner. This paper suggests a framework "Predictive Capability Maturity Quantification using Bayesian network (PCMQBN)" as a quantified framework for assessing simulation adequacy based on information collected from validation activities. A case study is prepared for evaluating the adequacy of a Smoothed Particle Hydrodynamic simulation in predicting the hydrodynamic forces onto static structures during an external flooding scenario. Comparing to the qualitative and implicit adequacy assessment, PCMQBN is able to improve confidence in the simulation adequacy result and to reduce expected loss in the risk-informed safety analysis.