This work presents an extensive study of transformer-based NLP models for detection of social media posts that contain verifiable factual claims and harmful claims. The study covers various activities, including dataset collection, dataset pre-processing, architecture selection, setup of settings, model training (fine-tuning), model testing, and implementation. The study includes a comprehensive analysis of different models, with a special focus on multilingual models where the same model is capable of processing social media posts in both English and in low-resource languages such as Arabic, Bulgarian, Dutch, Polish, Czech, Slovak. The results obtained from the study were validated against state-of-the-art models, and the comparison demonstrated the robustness of the proposed models. The novelty of this work lies in the development of multi-label multilingual classification models that can simultaneously detect harmful posts and posts that contain verifiable factual claims in an efficient way.

The credibility theory was introduced by B. Liu as a new way to describe the fuzzy uncertainty. The credibility measure is the fundamental notion of the credibility theory. Recently, L.Yang and K. Iwamura extended the credibility measure by defining the parametric measure $m_{\lambda}$ ($\lambda$ is a real parameter in the interval $[0,1]$ and for $\lambda= 1/2$ we obtain as a particular case the notion of credibility measure). By using the $m_{\lambda}$-measure, we studied in this paper a risk neutral multi-item inventory problem. Our construction generalizes the credibilistic inventory model developed by Y. Li and Y. Liu in 2019. In our model, the components of demand vector are fuzzy variables and the maximization problem is formulated by using the notion of $m_{\lambda}$-expected value. We shall prove a general formula for the solution of optimization problem, from which we obtained effective formulas for computing the optimal solutions in the particular cases where the demands are trapezoidal and triangular fuzzy numbers. For $\lambda=1/2$ we obtain as a particular case the computation formulas of the optimal solutions of the credibilistic inventory problem of Li and Liu. These computation formulas are applied for some $m_{\lambda}$-models obtained from numerical data.

Offensive language detection is a crucial task in today's digital landscape, where online platforms grapple with maintaining a respectful and inclusive environment. However, building robust offensive language detection models requires large amounts of labeled data, which can be expensive and time-consuming to obtain. Semi-supervised learning offers a feasible solution by utilizing labeled and unlabeled data to create more accurate and robust models. In this paper, we explore a few different semi-supervised methods, as well as data augmentation techniques. Concretely, we implemented eight semi-supervised methods and ran experiments for them using only the available data in the RO-Offense dataset and applying five augmentation techniques before feeding the data to the models. Experimental results demonstrate that some of them benefit more from augmentations than others.

Large language models (LLMs) exhibit remarkable in-context learning (ICL) capabilities. However, the underlying working mechanism of ICL remains poorly understood. Recent research presents two conflicting views on ICL: One attributes it to LLMs' inherent ability of task recognition, deeming label correctness and shot numbers of demonstrations as not crucial; the other emphasizes the impact of similar examples in the demonstrations, stressing the need for label correctness and more shots. In this work, we provide a Two-Dimensional Coordinate System that unifies both views into a systematic framework. The framework explains the behavior of ICL through two orthogonal variables: whether LLMs can recognize the task and whether similar examples are presented in the demonstrations. We propose the peak inverse rank metric to detect the task recognition ability of LLMs and study LLMs' reactions to different definitions of similarity. Based on these, we conduct extensive experiments to elucidate how ICL functions across each quadrant on multiple representative classification tasks. Finally, we extend our analyses to generation tasks, showing that our coordinate system can also be used to interpret ICL for generation tasks effectively.

Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC dramatically degraded. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the theory of automatic control, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Talor series expansion. The proposed CIC method possesses the property of Post-Training and plug-and-play which can be built on any existing advanced SIC methods. Experimental results on five public image compression datasets demonstrate that the proposed CIC outperforms five open-source state-of-the-art competing SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns.

The multi-agent spatial coverage control problem encompasses a broad research domain, dealing with both dynamic and static deployment strategies, discrete-task assignments, and spatial distribution-matching deployment. Coverage control may involve the deployment of a finite number of agents or a continuum through centralized or decentralized, locally-interacting schemes. All these problems can be solved via a different taxonomy of deployment algorithms for multiple agents. Depending on the application scenario, these problems involve from purely discrete descriptions of tasks (finite loads) and agents (finite resources), to a mixture of discrete and continuous elements, to fully continuous descriptions of the same. Yet, it is possible to find common features that underline all the above formulations, which we aim to illustrate here. By doing so, we aim to point the reader to novel references related to these problems. The short article outline is the following: Static coverage via concurrent area partitioning and assignment; Static coverage as a discrete task assignment; and Continuum task assignment for large-scale swarms.

Research in the field of language models is rapidly evolving, with many open models being released to the public. Openly available pretraining corpora usually focus on only a handful of languages, with many others either missing completely or extremely underrepresented. In this report, we introduce FuLG, a hundred-fifty-billion-token Romanian corpus extracted from CommonCrawl. We present our methodology for filtering FuLG and compare it via ablation studies against existing Romanian corpora.

In healthcare and medical diagnostics, Visual Question Answering (VQA) mayemergeasapivotal tool in scenarios where analysis of intricate medical images becomes critical for accurate diagnoses. Current text-based VQA systems limit their utility in scenarios where hands-free interaction and accessibility are crucial while performing tasks. A speech-based VQA system may provide a better means of interaction where information can be accessed while performing tasks simultaneously. To this end, this work implements a speech-based VQA system by introducing a Textless Multilingual Pathological VQA (TMPathVQA) dataset, an expansion of the PathVQA dataset, containing spoken questions in English, German & French. This dataset comprises 98,397 multilingual spoken questions and answers based on 5,004 pathological images along with 70 hours of audio. Finally, this work benchmarks and compares TMPathVQA systems implemented using various combinations of acoustic and visual features.

This introductory chapter provides an overview of the evolution and impact of Artificial Intelligence (AI) technologies in today's society. Beginning with a historical context while exploring a few general definitions of AI, the author provides a timeline of the used technologies, highlighting its periods of stagnation, commonly referred to as "AI winters," and the subsequent resurgence fueled by relentless enthusiasm and investment. The narrative then transitions to focus on the transformative effects of AI on society at large, with a particular emphasis on educational applications. Through examples, the paper shows how AI technologies have moved from theoretical constructs to practical tools that are reshaping pedagogical approaches and student engagement. The essay concludes by discussing the prospects of AI in education, emphasizing the need for a balanced approach that considers both technological advancements and societal implications. Introduction We have learned from our mistakes throughout history to adapt to a hostile environment. For example, after inventing fire, which often got out of control, we went on to invent fire extinguishers, fire alarms, and develop fire services. Similarly, the invention of gunpowder and firearms led to the creation of bulletproof vests and armor-plated vehicles and the development of guard and protection services. The invention of cars was followed by the introduction of seat belts, airbags, and, more recently, self-driving automobiles. It is safe to say that technology is an expression of human will. Through technological advancements, we seek to extend our control over various aspects of our environment - be it distance, nature, or even interpersonal dynamics. Each of the tools we developed possesses the power to influence our perspectives and shape the future (Vrabie & Eduard, 2018; Vrabie, 2016). For example, farming tools have revolutionized agricultural practices, and lab instruments have opened new frontiers for scientists. Books, maps, and similar devices, often called "intellectual technologies" (Goody & Bell, 1975), have expanded our world understanding. These last ones, in particular, have had the most significant impact on society as we know it.

Control systems used in Minimally Invasive Surgery (MIS) play a crucial role in ensuring preci-sion and safety throughout procedures. This paper presents a control architecture developed for a robotic system designed for MIS operations. The modular structure of the control system allows for compatibility with a range of procedures in abdominal and thoracic regions. The proposed control system, employing the master-slave concept, is presented alongside the experimental model. Functional validation is obtained by performing a Siemens NX simulation and comparing the results with several experimental runs using the experimental model of the robot. With its compact size and stiffness, the system holds promise for integration with other robotic systems. Future efforts will be dedicated to exploring and optimizing this potential collaboration to enhance the overall capabilities of robotic-assisted surgery.