Abstract Argument mining (AM) is an interdisciplinary research field focused on the automatic identification and classification of argumentative components, such as claims and premises, and the relationships between them. Recent advances in large language models (LLMs) have significantly improved the performance of argument classification compared to traditional machine learning approaches. However, there remains a lack of systematic comparative evaluation of modern LLMs across multiple benchmark datasets, as well as a limited understanding of their error patterns and failure modes. This study presents a comprehensive evaluation of several state-of-the-art LLMs, including GPT-5.2, Llama 4, and DeepSeek R1, on large publicly available argument classification corpora such as Args.me and UKP. The evaluation incorporates advanced prompting strategies, including Chain-of-Thought prompting, prompt rephrasing, voting, and certainty-based classification. Both quantitative performance metrics and qualitative error analysis are conducted to assess model behavior. The best-performing model in the study (GPT-5.2) achieves a classification accuracy of 78.0% (UKP) and 91.9% (Args.me). The use of prompt rephrasing, multi-prompt voting, and certainty estimation further improves classification performance and robustness. These techniques increase the accuracy and F1 metric of the modules by typically a few percentage points (from 2% to 8%). However, qualitative analysis reveals systematic failure modes shared across models, including instabilities with respect to prompt formulation, difficulties in detecting implicit criticism, interpreting complex argument structures, and aligning arguments with specific claims. The findings provide new insights into the strengths and limitations of LLMs in automated argument mining and highlight the importance of prompt engineering and ensemble techniques. This work contributes the first comprehensive evaluation that combines quantitative benchmarking and qualitative error analysis on multiple argument mining datasets using advanced LLM prompting strategies.

Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique combination of pruning with different sparsity levels, adaptive quantization, and weight sharing. Pruning identifies a subset of weights that preserve model performance, making less relevant weights available for future tasks. Adaptive quantization allows a single weight to be separated into multiple parts which can be assigned to different tasks. Weight sharing between tasks boosts the exploitation of capacity and task similarity, allowing for the identification of a better trade-off between model accuracy and capacity. These features allow TSN to efficiently leverage the available capacity, enhance knowledge transfer, and reduce computational resources consumption. Experimental results involving common benchmark CL datasets and scenarios show that our proposed strategy achieves better results in terms of accuracy than existing state-of-the-art CL strategies. Moreover, our strategy is shown to provide a significantly improved model capacity exploitation.

The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon forecasting and representation learning. This architecture has demonstrated success in time series forecasting, lossless compression, and even large-scale language modeling tasks, where its linear memory footprint and fast inference make it a viable alternative to Transformers. Despite its growing popularity, no prior work has explored xLSTM for anomaly detection. In this work, we fill this gap by proposing xLSTMAD, the first anomaly detection method that integrates a full encoder-decoder xLSTM architecture, purpose-built for multivariate time series data. Our encoder processes input sequences to capture historical context, while the decoder is devised in two separate variants of the method. In the forecasting approach, the decoder iteratively generates forecasted future values xLSTMAD-F, while the reconstruction approach reconstructs the input time series from its encoded counterpart xLSTMAD-R. We investigate the performance of two loss functions: Mean Squared Error (MSE), and Soft Dynamic Time Warping (SoftDTW) to consider local reconstruction fidelity and global sequence alignment, respectively. We evaluate our method on the comprehensive TSB-AD-M benchmark, which spans 17 real-world datasets, using state-of-the-art challenging metrics such as VUS-PR. In our results, xLSTM showcases state-of-the-art accuracy, outperforming 23 popular anomaly detection baselines. Our paper is the first work revealing the powerful modeling capabilities of xLSTM for anomaly detection, paving the way for exciting new developments on this subject. Our code is available at: https://github.com/Nyderx/xlstmad.

Medical image segmentation is crucial for clinical decision-making, treatment planning, and disease tracking. Nonetheless, it confronts two significant challenges: the presence of ''soft boundaries'' between the foreground and background exacerbated by poor illumination and low contrast, and the misleading co-occurrence of salient and non-salient objects during the training phase, which complicates the model's accuracy in distinguishing relevant features. To overcome these challenges, we introduce RoDeCon-Net, a novel framework engineered to enhance medical image segmentation. RoDeCon-Net incorporates a Feature Decoupling Unit (FDU) that dynamically separates encoded features into foreground, background, and uncertain regions, using advanced attention mechanisms to refine feature distinction and reduce uncertainty. Additionally, our Contrast-driven Feature Alignment Unit (CFAU) and Cross-layer Feature Cascade Unit (CFCU) synergize to reinforce feature contrasts and promote effective multi-level feature fusion, thus improving the detection of salient objects amidst complex backgrounds and handling various object scales within images. Comprehensive evaluations of RoDeCon-Net on five diverse medical image datasets validate its superior performance and versatility, showcasing its potential to set new benchmarks in medical image segmentation. Our code is available on https://github.com/ILoveACM-MM/RoDeCon-Net.

Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given dataset is a cumbersome and time-consuming process. Neuroevolution could be an effective and efficient solution to this problem, as a fully automated search method for learning optimal neural networks, supporting both gradient and nongradient fine-tuning. However, existing methods mostly focus on optimizing model architectures without taking into account feature subspaces and model weights. In this work, we propose anomaly detection neuroevolution (AD-NEv)-a scalable multilevel optimized neuroevolution framework for multivariate time-series anomaly detection. The method represents a novel approach to synergically: 1) optimize feature subspaces for an ensemble model based on the bagging technique; 2) optimize the model architecture of single anomaly detection models; and 3) perform nongradient fine-tuning of network weights. An extensive experimental evaluation on widely adopted multivariate anomaly detection benchmark datasets shows that the models extracted by AD-NEv outperform well-known deep learning architectures for anomaly detection. Moreover, results show that AD-NEv can perform the whole process efficiently, presenting high scalability when multiple graphics processing units (GPUs) are available.

Efficient flight scheduling is crucial to properly allocate airline resources, but even the best flight schedule has to face unexpected delays and disruptions. The ability to recover from such disruptions is essential for airlines to minimize the negative impact on their revenue and reputation. In this context, machine learning-based methods can be used to identify suitable recovery methods as unexpected events occur. Reinforcement learning approaches are especially promising since they extract suitable solutions much more efficiently than conventional optimization and meta-heuristics methods and provide timely rescheduling capabilities for airlines, which translates into reduced capital and reputation losses. However, current works either do not leverage deep learning or focus on simple scenarios that do not fully entail real-world complexities, resulting in limited efficiency or sub-optimal solutions. In this paper, we propose an ensemble of two deep learning approaches: Deep Double Q-Learning (DDQL) and Advantage Actor-Critic (A2C). The models aim to minimize the total delays caused by disruptions by swapping aircraft and delaying flights as recovery options. We perform experiments with a benchmark dataset and a real-world airline dataset, showing that our method is effective in providing a significant reduction of delays caused by disruptions.

Low Autocorrelation Binary Sequence (LABS) remains an open complex optimization problem with multiple applications.Existing studies rely primarily on advanced solvers based on local search heuristics, such as the steepest-descent local search algorithm (SDLS), Tabu search, or xLastovka algorithms.These approaches require searching through a large solution space, which is a computationally heavy and time-consuming process, leading to slower convergence.To improve convergence speed and allow for finding better solutions within a limited time, we propose the Deep Double Q-learning reinforcement learning algorithm for the LABS problem to support heuristic methods.The model aims to narrow down the search space without causing a drop in the final efficiency.Our experimental study showcases that the proposed approach is a promising direction for developing a highly efficient method for the LABS problem.* {dzurek, pietron, kpietak, kfaber}

Abstract Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in dynamic environments. This goal is realized by designing strategies that simultaneously foster the incorporation of new knowledge while avoiding forgetting past knowledge. The landscape of CL research is fragmented into several learning evaluation protocols, comprising different learning tasks, datasets, and evaluation metrics. Additionally, the benchmarks adopted so far are still distant from the complexity of real-world scenarios, and are usually tailored to highlight capabilities specific to certain strategies. In such a landscape, it is hard to clearly and objectively assess models and strategies. In this work, we fill this gap for CL on image data by introducing two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets, with varying levels of complexity and quality. Our aim is to fairly evaluate current state-of-the-art CL strategies on a common ground that is closer to complex real-world scenarios. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity—according to a curriculum—in order to evaluate if current CL models are able to exploit structure across tasks. We devote particular emphasis to providing the CL community with a rigorous and reproducible evaluation protocol for measuring the ability of a model to generalize and not to forget while learning. Furthermore, we provide an extensive experimental evaluation showing that popular CL strategies, when challenged with our proposed benchmarks, yield sub-par performance, high levels of forgetting, and present a limited ability to effectively leverage curriculum task ordering. We believe that these results highlight the need for rigorous comparisons in future CL works as well as pave the way to design new CL strategies that are able to deal with more complex scenarios.

Continual learning (CL) is a challenging machine learning setting that is attracting the interest of an increasing number of researchers. Among recent CL works, architectural strategies appear particularly promising due to their potential to expand and adapt the model architecture as new tasks are presented. However, existing solutions do not efficiently exploit model sparsity due to the adoption of constant pruning ratios. Moreover, current approaches exhibit a tendency to quickly saturate model capacity since the number of weights is limited and each weight is restricted to a single value. In this paper, we propose Ada-QPacknet, a novel architectural CL method that resorts to adaptive pruning and quantization. These two features allow our model to overcome the two crucial issues of effective exploitation of model sparsity and efficient use of model capacity. Specifically, adaptive pruning restores model capacity by reducing the number of weights assigned to each task to a smaller subset of weights that preserves the performance of the full set, allowing other weights to be used for future tasks. Adaptive quantization separates each weight into multiple components with adaptively reduced bit-width, allowing a single weight to solve more than one task without significant performance drops, leading to improved exploitation of model capacity. Experimental results on benchmark CL scenarios show that our proposed method achieves better results in terms of accuracy than existing rehearsal, regularization, and architectural CL strategies. Moreover, our method significantly outperforms forget-free competitors in terms of efficient exploitation of model capacity.

Lifelong learning is becoming a popular trend in modern machine learning research. Domain-incremental scenarios are particularly relevant since they closely reflects real-world characteristics. However, one open challenge is the ability to devise scenarios that entail the inherent unpredictability and complexities of domains still unexplored in lifelong learning. To tackle this issue, we propose a framework for domain-incremental scenario generation. The framework enables users to create lifelong learning scenarios using any image dataset, and leveraging a fully customizable pool of transformation functions. We devise an algorithm and criteria that iteratively guide users in evaluating the inclusion of candidate transformation functions to the scenario and in making this decision based on desired outcomes. Experimental results with common lifelong learning strategies and benchmark datasets show that our framework is highly flexible since it allows tweaking complexities and challenges incorporated in generated scenarios. Furthermore, experimental results show that there is a gap between state-of-the-art learning strategies and a proposed upper bound to be exploited in the design of future learning strategies.

The main goal of this work was to implement a reliable machine learning algorithm that can classify a dog's age given only a photograph of its face.The problem, which seems simple for humans, presents itself as very difficult for the machine learning algorithms due to differences in facial features among the dog population.As convolutional neural networks (CNNs) performed poorly in this problem, the authors took another approach of creating novel architecture consisting of a combination of CNN and vision transformer (ViT) and examining the age of the dogs separately for every breed.Authors achieved better results than those in initial works covering the problem.

This paper presents the analysis of the impact of a floating-point number precision reduction on the quality of text classification. The precision reduction of the vectors representing the data (e.g. TF-IDF representation in our case) allows for a decrease of computing time and memory footprint on dedicated hardware platforms. The impact of precision reduction on the classification quality was performed on 5 corpora, using 4 different classifiers. Also, dimensionality reduction was taken into account. Results indicate that the precision reduction improves classification accuracy for most cases (up to 25% of error reduction). In general, the reduction from 64 to 4 bits gives the best scores and ensures that the results will not be worse than with the full floating-point representation.

This paper focuses on analyzing a Spatial Pooler (SP) of Hierarchical Temporal Memory (HTM) ability for facilitating object classification in noisy video streams.In particular, we seek to determine whether employing SP as a component of the video system increases overall robustness to noise.We have implemented our own version of HTM and applied it to object recognition tasks under various testing conditions.The system is composed of a video preprocessing block, a dimensionality reduction section which contains SP, a histograms collecting module and SVM classifier.Our experiments involve assessing performance of two different system setups (i.e. a version featuring SP and one without it) under various noise conditions with 32-frame video files.In order to make tests fair and repeatable the videos of several 3-D geometric shapes were artificially generated.Subsequently, Gaussian noise of a different intensity was introduced to the videos making them more indistinct.Such an approach mimics real-life scenarios where the system is taught ideal objects and then faces in its normal working conditions the challenge of detecting noisy ones.The results of the experiments reveal the superiority of the solution featuring Spatial Pooler over the one without it.Furthermore, the system with SP performed better also in the experiment without a noise component introduced and achieved a mean F1-score of 0.91 in ten trials.

The presented algorithms employ the Vector Space Model (VSM) and its enhancements such as TFIDF (Term Frequency Inverse Document Frequency). Vector space model suffers from curse of dimensionality. Therefore various dimensionality reduction algorithms are utilized. This paper deals with two of the most common ones i.e. Latent Semantic Indexing (LSI) and Random Projection (RP). It turns out that the size of a document corpus has a substantial impact on the processing time. Thus the authors introduce GPU based on acceleration of these techniques. A dedicated test set-up was created and a series of experiments were conducted which revealed important properties of the algorithms and their accuracy. They show that the random projection outperforms LSI in terms of computing speed at the expanse of results quality.