The rapid expansion of the Industrial Internet of Things (IIoT) has significantly advanced digital technologies and interconnected industrial systems, creating substantial opportunities for growth. However, this growth has also heightened the risk of cyberattacks, necessitating robust security measures to protect IIoT networks. Intrusion Detection Systems (IDS) are essential for identifying and preventing abnormal network behaviors and malicious activities. Despite the potential of Machine Learning (ML)--based IDS solutions, existing models often face challenges with class imbalance and multiclass IIoT datasets, resulting in reduced detection accuracy. This research directly addresses these challenges by implementing six innovative approaches to enhance IDS performance, including leveraging an autoencoder for dimensional reduction, which improves feature learning and overall detection accuracy. Our proposed Decision Tree model achieved an exceptional F1 score and accuracy of 99.94% on the Edge-IIoTset dataset. Furthermore, we prioritized lightweight model design, ensuring deployability on resource-constrained edge devices. Notably, we are the first to deploy our model on a Jetson Nano, achieving inference times of 0.185 ms for binary classification and 0.187 ms for multiclass classification. These results highlight the novelty and robustness of our approach, offering a practical and efficient solution to the challenges posed by imbalanced and multiclass IIoT datasets, thereby enhancing the detection and prevention of network intrusions.

Considering the significance of proteins, computational protein science has always been a critical scientific field, dedicated to revealing knowledge and developing applications within the protein sequence-structure-function paradigm. In the last few decades, Artificial Intelligence (AI) has made significant impacts in computational protein science, leading to notable successes in specific protein modeling tasks. However, those previous AI models still meet limitations, such as the difficulty in comprehending the semantics of protein sequences, and the inability to generalize across a wide range of protein modeling tasks. Recently, LLMs have emerged as a milestone in AI due to their unprecedented language processing & generalization capability. They can promote comprehensive progress in fields rather than solving individual tasks. As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems. While witnessing prosperous developments, it's necessary to present a systematic overview of computational protein science empowered by LLM techniques. First, we summarize existing pLMs into categories based on their mastered protein knowledge, i.e., underlying sequence patterns, explicit structural and functional information, and external scientific languages. Second, we introduce the utilization and adaptation of pLMs, highlighting their remarkable achievements in promoting protein structure prediction, protein function prediction, and protein design studies. Then, we describe the practical application of pLMs in antibody design, enzyme design, and drug discovery. Finally, we specifically discuss the promising future directions in this fast-growing field.

This paper presents an approach that combines Human-In-The-Loop Reinforcement Learning (HITL RL) with principles derived from music theory to facilitate real-time generation of musical compositions. HITL RL, previously employed in diverse applications such as modelling humanoid robot mechanics and enhancing language models, harnesses human feedback to refine the training process. In this study, we develop a HILT RL framework that can leverage the constraints and principles in music theory. In particular, we propose an episodic tabular Q-learning algorithm with an epsilon-greedy exploration policy. The system generates musical tracks (compositions), continuously enhancing its quality through iterative human-in-the-loop feedback. The reward function for this process is the subjective musical taste of the user.

The use of chatbots in language learning has evolved significantly since the 1960s, becoming more sophisticated platforms as generative AI emerged. These tools now simulate natural conversations, adapting to individual learners' needs, including those studying Chinese. Our study explores how learners can use specific prompts to engage Large Language Models (LLM) as personalized chatbots, aiming to target their language level based on the Common European Framework of Reference for Languages (CEFR) and the European Benchmarking Chinese Language (EBCL) project. Focusing on A1, A1+ and A2 levels, we examine the teaching of Chinese, which presents unique challenges due to its logographic writing system. Our goal is to develop prompts that integrate oral and written skills, using high-frequency character lists and controlling oral lexical productions. These tools, powered by generative AI, aim to enhance language practice by crossing lexical and sinographic recurrence. While generative AI shows potential as a personalized tutor, further evaluation is needed to assess its effectiveness. We conducted a systematic series of experiments using ChatGPT models to evaluate their adherence to constraints specified in the prompts. The results indicate that incorporating level A1 and A1+ characters, along with the associated reference list, significantly enhances compliance with the EBCL character set. Properly prompted, LLMs can increase exposure to the target language and offer interactive exchanges to develop language skills.

The increasing sophistication of encryption-based ransomware has demanded innovative approaches to detection and mitigation, prompting the development of a hierarchical framework grounded in probabilistic cryptographic analysis. By focusing on the statistical characteristics of encryption patterns, the proposed methodology introduces a layered approach that combines advanced clustering algorithms with machine learning to isolate ransomware-induced anomalies. Through comprehensive testing across diverse ransomware families, the framework demonstrated exceptional accuracy, effectively distinguishing malicious encryption operations from benign activities while maintaining low false positive rates. The system's design integrates dynamic feedback mechanisms, enabling adaptability to varying cryptographic complexities and operational environments. Detailed entropy-based evaluations revealed its sensitivity to subtle deviations in encryption workflows, offering a robust alternative to traditional detection methods reliant on static signatures or heuristics. Computational benchmarks confirmed its scalability and efficiency, achieving consistent performance even under high data loads and complex cryptographic scenarios. The inclusion of real-time clustering and anomaly evaluation ensures rapid response capabilities, addressing critical latency challenges in ransomware detection. Performance comparisons with established methods highlighted its improvements in detection efficacy, particularly against advanced ransomware employing extended key lengths and unique cryptographic protocols.

Unfortunately reviewer_2 did not engage in the discussion even though it was needed, my recommendation is thus mainly based on the 3 other reviews. This paper investigates the expressive power of Graph neural networks by studying to which extent they can compute graph moments. This is an interesting and original approach and the theoretical findings are sound and relevant to the community. In preparing the camera-ready version of the paper, the authors should take the following points in consideration. The reviewers mentioned that the exposition of some of the contributions are somehow overstated and should be tuned down.

The GW distance produces as a byproduct of its computation a transportation coupling, which can be used to infer node-to-node correspondences between graphs. In addition, the optimal transport framework has the appealing property of generalizing to multi-distribution comparisons thorough barycenters, which is exploited in this work to yield joint multi-graph approaches to partitioning and matching. Instead of a the more traditional projected gradient descent approach, the authors rely on a regularized proximal gradient method to compute the GW distance and barycenters. In order to scale up to large graphs, they propose a recursive divide-and-conquer approach. Various experiments on benchmark graph/network partitioning and matching tasks are performed, showing that the proposed method compares favorably (both in terms of accuracy and runtime) to various popular baselines. Strengths: - Strong theoretical foundations (the Gromov-Wasserstein distance) to a task often approach with heuristic methods - Superbly written paper: clear and concise argumentation, easy to follow, and a pleasure to read - The thorough experimental results, which show that the proposed approach is effective and efficient in practice - Rigorous and comprehensive review of computational complexities of the proposed alternative methods Weaknesses: - Limited novelty of methods / theory Major Comments/Questions: 1. Novelty/Contributions. While GW has been used for graph matching repeatedly in previous work (albeit for small tasks - see below), I am not aware of other work that uses it for graph partitioning, so I would consider this an important contribution of this paper. It should be noted that most of the individual components used in this work are not novel (the GW itself, its application to graph matching, the proximal gradient method). However, I see consider its main contribution combining those components in a coherent and practical way, and producing as a consequence a promising and well-founded approach to two important tasks.

Differential privacy has emerged as the most studied framework for privacy-preserving machine learning. However, recent studies show that enforcing differential privacy guarantees can not only significantly degrade the utility of the model, but also amplify existing disparities in its predictive performance across demographic groups. Although there is extensive research on the identification of factors that contribute to this phenomenon, we still lack a complete understanding of the mechanisms through which differential privacy exacerbates disparities. The literature on this problem is muddled by varying definitions of fairness, differential privacy mechanisms, and inconsistent experimental settings, often leading to seemingly contradictory results. This survey provides the first comprehensive overview of the factors that contribute to the disparate effect of training models with differential privacy guarantees. We discuss their impact and analyze their causal role in such a disparate effect. Our analysis is guided by a taxonomy that categorizes these factors by their position within the machine learning pipeline, allowing us to draw conclusions about their interaction and the feasibility of potential mitigation strategies. We find that factors related to the training dataset and the underlying distribution play a decisive role in the occurrence of disparate impact, highlighting the need for research on these factors to address the issue.

Automated grading has become an essential tool in education technology due to its ability to efficiently assess large volumes of student work, provide consistent and unbiased evaluations, and deliver immediate feedback to enhance learning. However, current systems face significant limitations, including the need for large datasets in few-shot learning methods, a lack of personalized and actionable feedback, and an overemphasis on benchmark performance rather than student experience. To address these challenges, we propose a Zero-Shot Large Language Model (LLM)-Based Automated Assignment Grading (AAG) system. This framework leverages prompt engineering to evaluate both computational and explanatory student responses without requiring additional training or fine-tuning. The AAG system delivers tailored feedback that highlights individual strengths and areas for improvement, thereby enhancing student learning outcomes. Our study demonstrates the system's effectiveness through comprehensive evaluations, including survey responses from higher education students that indicate significant improvements in motivation, understanding, and preparedness compared to traditional grading methods. The results validate the AAG system's potential to transform educational assessment by prioritizing learning experiences and providing scalable, high-quality feedback.

Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is multiplicity-the study of arbitrariness across a set of "good models", i.e., those likely to be deployed in practice. In this work, we systemize the literature on multiplicity by: (a) formalizing the terminology around model design choices and their contribution to arbitrariness, (b) expanding the definition of multiplicity to incorporate underrepresented forms beyond just predictions and explanations, (c) clarifying the distinction between multiplicity and other traditional lenses of arbitrariness, i.e., uncertainty and variance, and (d) distilling the benefits and potential risks of multiplicity into overarching trends, situating it within the broader landscape of responsible AI. We conclude by identifying open research questions and highlighting emerging trends in this young but rapidly growing area of research.