Metadata management plays a critical role in data governance, resource discovery, and decision-making in the data-driven era. While traditional metadata approaches have primarily focused on organization, classification, and resource reuse, the integration of modern artificial intelligence (AI) technologies has significantly transformed these processes. This paper investigates both traditional and AI-driven metadata approaches by examining open-source solutions, commercial tools, and research initiatives. A comparative analysis of traditional and AI-driven metadata management methods is provided, highlighting existing challenges and their impact on next-generation datasets. The paper also presents an innovative AI-assisted metadata management framework designed to address these challenges. This framework leverages more advanced modern AI technologies to automate metadata generation, enhance governance, and improve the accessibility and usability of modern datasets. Finally, the paper outlines future directions for research and development, proposing opportunities to further advance metadata management in the context of AI-driven innovation and complex datasets.

Reinforcement learning (RL) has demonstrated success in automating insulin dosing in simulated type 1 diabetes (T1D) patients but is currently unable to incorporate patient expertise and preference. This work introduces PAINT (Preference Adaptation for INsulin control in T1D), an original RL framework for learning flexible insulin dosing policies from patient records. PAINT employs a sketch-based approach for reward learning, where past data is annotated with a continuous reward signal to reflect patient's desired outcomes. Labelled data trains a reward model, informing the actions of a novel safety-constrained offline RL algorithm, designed to restrict actions to a safe strategy and enable preference tuning via a sliding scale. In-silico evaluation shows PAINT achieves common glucose goals through simple labelling of desired states, reducing glycaemic risk by 15% over a commercial benchmark. Action labelling can also be used to incorporate patient expertise, demonstrating an ability to pre-empt meals (+10% time-in-range post-meal) and address certain device errors (-1.6% variance post-error) with patient guidance. These results hold under realistic conditions, including limited samples, labelling errors, and intra-patient variability. This work illustrates PAINT's potential in real-world T1D management and more broadly any tasks requiring rapid and precise preference learning under safety constraints.

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existing research on adversarial applications of generative AI predominantly focuses on cyberattacks, less attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of generative AI for facilitating model-related attacks, including model extraction, membership inference, and model inversion. Our study reveals that adversaries can launch a variety of model-related attacks against both image and text models in a data-free and black-box manner, achieving comparable performance to baseline methods that have access to the target models' training data and parameters in a white-box manner. This research serves as an important early warning to the community about the potential risks associated with generative AI-powered attacks on deep learning models.

Virtually all verification techniques using formal methods rely on the availability of a formal specification, which describes the design requirements precisely. However, formulating specifications remains a manual task that is notoriously challenging and error-prone. To address this bottleneck in formal verification, recent research has thus focussed on automatically generating specifications for formal verification from examples of (desired and undesired) system behavior. In this survey, we list and compare recent advances in mining specifications in Linear Temporal Logic (LTL), the de facto standard specification language for reactive systems. Several approaches have been designed for learning LTL formulas, which address different aspects and settings of specification design. Moreover, the approaches rely on a diverse range of techniques such as constraint solving, neural network training, enumerative search, etc. We survey the current state-of-the-art techniques and compare them for the convenience of the formal methods practitioners.

This paper studies the problem of cross lingual language model pretraining. Pros • An important problem is studied. Cons • The proposed methods are not particularly novel. All the reviewers liked the paper.

Additional Feedback: Major: - Why the SCIP solver was used as a baseline and not Gurobi? My experience suggests that Gurobi typically performs notably better and the academic license is free. It seems you unintentionally deleted a part of it. Minor: - I would suggest to use the term "volume" instead of "cost", as it makes more sense to restrict the volume and maximize the profit than to restrict the costs and maximize the profit, especially when one speaks about a knapsack (with a predefined volume). It becomes more readable, if you would write "m is the number of log-potentials, i.e. m \mathbf(f) ". x l argmax ..., x u argmin ... l155: the sentence "and a real number q such that no two functions ... share any variable..." - is ambiguous. Put "and a real number q" right before "we can construct" instead.

The paper proposes a new inference task for graphical models. It consists in finding a MAP assignment w.r.t. It contains as special cases several interesting graphical model problems like m-best assigments. The method uses a transformation to multiple choice knapsack for cmputationally solving the problem. Authors agree that the new problem is interesting and the transformation to multiple choice knapsack is interesting. The main criticism pertains to the small experiments that are not necessarily indicative of real-world problems.

The paper shows that accurate wind speed measurements in real time can be done using a suitable deep net based on visual observations such as flapping of flags or swaying of trees. The deep net considered is a coupled CNN and RNN. The results illustrate the approach to be accurate and discussions are provided for the challenges in the high and the low wind speeds, respectively called the frame rate limited zone and the duration limited zone. The reviewers agreed that the paper presents an interesting dataset and proposes a creative approach using existing machine learning models. The reviewers felt that due to the novelty of the application domain, novel machine learning approaches are not a requirement.

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables or linear approximators to map state-action tuples that maximises the reward. Combining RL with deep neural networks (DRL) significantly increases its scalability and enables it to address more complex problems than before. However, DRL also inherits downsides from both RL and deep learning. Despite DRL improves generalisation across similar state-action pairs when compared to simpler RL policy representations like tabular methods, it still requires the agent to adequately explore the state-action space. Additionally, deep methods require more training data, with the volume of data escalating with the complexity and size of the neural network. As a result, deep RL requires a long time to collect enough agent-environment samples and to successfully learn the underlying policy. Furthermore, often even a slight alteration to the task invalidates any previous acquired knowledge. To address these shortcomings, Transfer Learning (TL) has been introduced, which enables the use of external knowledge from other tasks or agents to enhance a learning process. The goal of TL is to reduce the learning complexity for an agent dealing with an unfamiliar task by simplifying the exploration process. This is achieved by lowering the amount of new information required by its learning model, resulting in a reduced overall convergence time...

This study investigates the potential of hybrid metaheuristic algorithms to enhance the training of Probabilistic Neural Networks (PNNs) by leveraging the complementary strengths of multiple optimisation strategies. Traditional learning methods, such as gradient-based approaches, often struggle to optimise high-dimensional and uncertain environments, while single-method metaheuristics may fail to exploit the solution space fully. To address these challenges, we propose the constrained Hybrid Metaheuristic (cHM) algorithm, a novel approach that combines multiple population-based optimisation techniques into a unified framework. The proposed procedure operates in two phases: an initial probing phase evaluates multiple metaheuristics to identify the best-performing one based on the error rate, followed by a fitting phase where the selected metaheuristic refines the PNN to achieve optimal smoothing parameters. This iterative process ensures efficient exploration and convergence, enhancing the network's generalisation and classification accuracy. cHM integrates several popular metaheuristics, such as BAT, Simulated Annealing, Flower Pollination Algorithm, Bacterial Foraging Optimization, and Particle Swarm Optimisation as internal optimisers. To evaluate cHM performance, experiments were conducted on 16 datasets with varying characteristics, including binary and multiclass classification tasks, balanced and imbalanced class distributions, and diverse feature dimensions. The results demonstrate that cHM effectively combines the strengths of individual metaheuristics, leading to faster convergence and more robust learning. By optimising the smoothing parameters of PNNs, the proposed method enhances classification performance across diverse datasets, proving its application flexibility and efficiency.