Grounded in critical realism and using narrative inquiry, this article explores this article explores the long - term consequences of the COVID - 19 pandemic and the rapid proliferation of artificial intelligence within higher education. Through the analysis of student narratives collected in Iranian university settings, the study reveals that learning experiences during and after the pandemic, coupled with unprepared exposure to AI tools, have generated hidden yet impactful layers of educational inequality and cognitive disorientation. These twin phenomena have not only disrupted traditio nal structures of learning but also carry the potential to deepen existing epistemic and social disparities. The article argues that the university can only fulfill its mission if it develops the epistemic tools necessary to trace layered realities and eng age seriously with the often - silenced narratives embedded in students' lived experiences. Such an approach requires a fundamental rethinking in regard to university's role in a rapidly changing educational and technological landscape.

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an extensive study aimed at advancing recent RL-based finetuning techniques for LLMs in the context of vulnerability detection. We start by highlighting key limitations of commonly adopted LLMs, such as their tendency to over-predict certain types of vulnerabilities while failing to detect others. To address this challenge, we explore the use of Group Relative Policy Optimization (GRPO), a recent policy-gradient method, for guiding LLM behavior through structured, rule-based rewards. We enable its application to the vulnerability detection task by redefining its advantage functions and reward signals using annotations from widely used datasets in the field, including BigVul, DiverseVul, and CleanVul. The proposed methodology enables an extensive set of experiments, addressing multiple research questions regarding the impact of GRPO on generalization, reasoning capabilities, and performance improvements over standard supervised finetuning (SFT). Our findings offer valuable insights into the potential of RL-based training to enhance both the performance and reasoning abilities of LLMs in the context of software vulnerability detection.

--The Artificial Intelligence field has focused on developing optimisation methods to solve multiple problems, specifically problems that we thought to be only solvable through cognition. The obtained results have been outstanding, being able to even surpass the T uring T est. However, we have found that these optimisation methods share some fundamental flaws that impede them to become a true artificial cognition. Specifically, the field have identified catastrophic forgetting as a fundamental problem to develop such cognition. This paper formally proves that this problem is inherent to optimisation methods, and as such it will always limit approaches that try to solve the Artificial General Intelligence problem as an optimisation problem. Additionally, it addresses the problem of overfitting and discuss about other smaller problems that optimisation methods pose. Finally, it empirically shows how world-modelling methods avoid suffering from either problem. As a conclusion, the field of Artificial Intelligence needs to look outside the machine learning field to find methods capable of developing an artificial cognition. HERE is a common goal in the Artificial Intelligence field: approaching the achievement of an artificial cognition by producing results similar to those produced by a natural cognition (i.e. a human). That is, the efforts in such field have been focused on mimicking the effects of cognition. This approach has produced a plethora of optimisation methods that try to solve problems that are considered solvable only by humans. The underlying assumption was that, if some algorithm is able to solve these problems, it will be due to the emergence of cognition (or at least some kind of cognition-like reasoning).

This research investigates the efficacy of machine learning (ML) and deep learning (DL) methods in detecting misclassified intersection-related crashes in police-reported narratives. Using 2019 crash data from the Iowa Department of Transportation, we implemented and compared a comprehensive set of models, including Support Vector Machine (SVM), XGBoost, BERT Sentence Embeddings, BERT Word Embeddings, and Albert Model. Model performance was systematically validated against expert reviews of potentially misclassified narratives, providing a rigorous assessment of classification accuracy. Results demonstrated that while traditional ML methods exhibited superior overall performance compared to some DL approaches, the Albert Model achieved the highest agreement with expert classifications (73% with Expert 1) and original tabular data (58%). Statistical analysis revealed that the Albert Model maintained performance levels similar to inter-expert consistency rates, significantly outperforming other approaches, particularly on ambiguous narratives. This work addresses a critical gap in transportation safety research through multi-modal integration analysis, which achieved a 54.2% reduction in error rates by combining narrative text with structured crash data. We conclude that hybrid approaches combining automated classification with targeted expert review offer a practical methodology for improving crash data quality, with substantial implications for transportation safety management and policy development.

We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image, our method operates on an entire concept -- represented by a probabilistic generative model or a set of images -- to generate diverse adversarial examples. Preserving the concept is essential, as it ensures that the resulting adversarial images remain identifiable as instances of the original underlying category or identity. By sampling from this concept-based adversarial distribution, we generate images that maintain the original concept but vary in pose, viewpoint, or background, thereby misleading the classifier. Mathematically, this framework remains consistent with traditional adversarial attacks in a principled manner. Our theoretical and empirical results demonstrate that concept-based adversarial attacks yield more diverse adversarial examples and effectively preserve the underlying concept, while achieving higher attack efficiency.

Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs, especially for low-resource languages, faces significant challenges arising from data-sharing restrictions (the physical border) and inherent linguistic differences (the linguistic border). These barriers hinder users of various languages, particularly those in low-resource regions, from fully benefiting from the advantages of LLMs. To address these challenges, we propose the Federated Prompt Tuning Paradigm for multilingual scenarios, which utilizes parameter-efficient fine-tuning while adhering to data sharing restrictions. We design a comprehensive set of experiments and analyze them using a novel notion of language distance to highlight the strengths of our paradigm: Even under computational constraints, our method not only improves data efficiency but also facilitates mutual enhancements across languages, particularly benefiting low-resource ones. Compared to traditional local cross-lingual transfer tuning methods, our approach achieves 6.9\% higher accuracy with improved data efficiency, and demonstrates greater stability and generalization. These findings underscore the potential of our approach to promote social equality and champion linguistic diversity, ensuring that no language is left behind.

Remote sensing change detection aims to localize semantic changes between images of the same location captured at different times. In the past few years, newer methods have attributed enhanced performance to the additions of new and complex components to existing architectures. Most fail to measure the performance contribution of fundamental design choices such as backbone selection, pre-training strategies, and training configurations. We claim that such fundamental design choices often improve performance even more significantly than the addition of new architectural components. Due to that, we systematically revisit the design space of change detection models and analyse the full potential of a well-optimised baseline. We identify a set of fundamental design choices that benefit both new and existing architectures. Leveraging this insight, we demonstrate that when carefully designed, even an architecturally simple model can match or surpass state-of-the-art performance on six challenging change detection datasets. Our best practices generalise beyond our architecture and also offer performance improvements when applied to related methods, indicating that the space of fundamental design choices has been underexplored. Our guidelines and architecture provide a strong foundation for future methods, emphasizing that optimizing core components is just as important as architectural novelty in advancing change detection performance. Code: https://github.com/blaz-r/BTC-change-detection

We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths: the cost of processing the context is too expensive in the former, too inexpensive in the latter. Approaches such as sliding window attention which reduce the cost-per-token of a transformer impair in-context learning, and so are also unsuitable. To address these limitations, we introduce power attention, an architectural layer for linear-cost sequence modeling whose state size can be adjusted independently of parameters, unlocking the advantages of linear attention on practical domains. We develop and open-source a set of GPU kernels for efficient power attention, identifying a novel pattern of operation fusion to avoid memory and bandwidth bottlenecks. Our experiments on the in-context learning of power attention shows that these models dominate both exponential attention and linear attention at long-context training.

Machine learning enables the extraction of useful information from large, diverse datasets. However, despite many successful applications, machine learning continues to suffer from performance and transparency issues. These challenges can be partially attributed to the limited use of domain knowledge by machine learning models. This research proposes using the domain knowledge represented in conceptual models to improve the preparation of the data used to train machine learning models. We develop and demonstrate a method, called the Conceptual Modeling for Machine Learning (CMML), which is comprised of guidelines for data preparation in machine learning and based on conceptual modeling constructs and principles. To assess the impact of CMML on machine learning outcomes, we first applied it to two real-world problems to evaluate its impact on model performance. We then solicited an assessment by data scientists on the applicability of the method. These results demonstrate the value of CMML for improving machine learning outcomes.

This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We conduct a literature search via Scopus and Google Scholar, examining over 2,000 publications. We assess publications against four inclusion and four exclusion criteria related to their language, research focus, publication year, and type. Eventually, we select 103 studies. We classify these studies into semantic categories and topics to provide a comprehensive overview of the field, including the tasks performed by LLMs, the architectures of LLMs, the existing datasets specifically designed for evaluating LLMs in CO, and the field of application. Finally, we identify future directions for leveraging LLMs in this field.