We introduce milearn, a Python package for multi-instance learning (MIL) that follows the familiar scikit-learn fit/predict interface while providing a unified framework for both classical and neural-network-based MIL algorithms for regression and classification. The package also includes built-in hyperparameter optimization designed specifically for small MIL datasets, enabling robust model selection in data-scarce scenarios. We demonstrate the versatility of milearn across a broad range of synthetic MIL benchmark datasets, including digit classification and regression, molecular property prediction, and protein-protein interaction (PPI) prediction. Special emphasis is placed on the key instance detection (KID) problem, for which the package provides dedicated support.

In this paper, the branches of recursive and recurrent neural networks are classified in detail according to the network structure, training objective function and learning algorithm implementation. They are roughly divided into three categories: The first category is General Recursive and Recurrent Neural Networks, including Basic Recursive and Recurrent Neural Networks, Long Short Term Memory Recursive and Recurrent Neural Networks, Convolutional Recursive and Recurrent Neural Networks, Differential Recursive and Recurrent Neural Networks, One-Layer Recursive and Recurrent Neural Networks, High-Order Recursive and Recurrent Neural Networks, Highway Networks, Multidimensional Recursive and Recurrent Neural Networks, Bidirectional Recursive and Recurrent Neural Networks; the second category is Structured Recursive and Recurrent Neural Networks, including Grid Recursive and Recurrent Neural Networks, Graph Recursive and Recurrent Neural Networks, Temporal Recursive and Recurrent Neural Networks, Lattice Recursive and Recurrent Neural Networks, Hierarchical Recursive and Recurrent Neural Networks, Tree Recursive and Recurrent Neural Networks; the third category is Other Recursive and Recurrent Neural Networks, including Array Long Short Term Memory, Nested and Stacked Recursive and Recurrent Neural Networks, Memory Recursive and Recurrent Neural Networks. Various networks cross each other and even rely on each other to form a complex network of relationships. In the context of the development and convergence of various networks, many complex sequence, speech and image problems are solved. After a detailed description of the principle and structure of the above model and model deformation, the research progress and application of each model are described, and finally the recursive and recurrent neural network models are prospected and summarized.

Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage trajectory, i.e., whether tools are selected, parameterized, and ordered correctly. We introduce TRAJECT-Bench, a trajectory-aware benchmark to comprehensively evaluate LLMs' tool use capability through diverse tasks with fine-grained evaluation metrics. TRAJECT-Bench pairs high-fidelity, executable tools across practical domains with tasks grounded in production-style APIs, and synthesizes trajectories that vary in breadth (parallel calls) and depth (interdependent chains). Besides final accuracy, TRAJECT-Bench also reports trajectory-level diagnostics, including tool selection and argument correctness, and dependency/order satisfaction. Analyses reveal failure modes such as similar tool confusion and parameter-blind selection, and scaling behavior with tool diversity and trajectory length where the bottleneck of transiting from short to mid-length trajectories is revealed, offering actionable guidance for LLMs' tool use.

Background: Pleural Effusions (PE) is a common finding in many different clinical conditions, but accurately measuring their volume from CT scans is challenging. Purpose: To improve PE segmentation and quantification for enhanced clinical management, we have developed and trained a semi-supervised deep learning framework on contrast-enhanced CT volumes. Materials and Methods: This retrospective study collected CT Pulmonary Angiogram (CTPA) data from internal and external datasets. A subset of 100 cases was manually annotated for model training, while the remaining cases were used for testing and validation. A novel semi-supervised deep learning framework, Teacher-Teaching Assistant-Student (TTAS), was developed and used to enable efficient training in non-segmented examinations. Segmentation performance was compared to that of state-of-the-art models. Results: 100 patients (mean age, 72 years, 28 [standard deviation]; 55 men) were included in the study. The TTAS model demonstrated superior segmentation performance compared to state-of-the-art models, achieving a mean Dice score of 0.82 (95% CI, 0.79 - 0.84) versus 0.73 for nnU-Net (p < 0.0001, Student's T test). Additionally, TTAS exhibited a four-fold lower mean Absolute Volume Difference (AbVD) of 6.49 mL (95% CI, 4.80 - 8.20) compared to nnU-Net's AbVD of 23.16 mL (p < 0.0001). Conclusion: The developed TTAS framework offered superior PE segmentation, aiding accurate volume determination from CT scans.

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often falls short compared to classical methods, which we show is largely due to their increased susceptibility to overfitting. This work therefore investigates regularization methods for training ASR models with learnable feature extraction front-ends. First, we examine audio perturbation methods and show that larger relative improvements can be obtained for learnable features. Additionally, we identify two limitations in the standard use of SpecAugment for these front-ends and propose masking in the short time Fourier transform (STFT)-domain as a simple but effective modification to address these challenges. Finally, integrating both regularization approaches effectively closes the performance gap between traditional and learnable features.

Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks.

This paper presents a comprehensive analysis of various static word embeddings for Hungarian, including traditional models such as Word2Vec, FastText, as well as static embeddings derived from BERT-based models using different extraction methods. We evaluate these embeddings on both intrinsic and extrinsic tasks to provide a holistic view of their performance. For intrinsic evaluation, we employ a word analogy task, which assesses the embeddings ability to capture semantic and syntactic relationships. Our results indicate that traditional static embeddings, particularly FastText, excel in this task, achieving high accuracy and mean reciprocal rank (MRR) scores. Among the BERT-based models, the X2Static method for extracting static embeddings demonstrates superior performance compared to decontextualized and aggregate methods, approaching the effectiveness of traditional static embeddings. For extrinsic evaluation, we utilize a bidirectional LSTM model to perform Named Entity Recognition (NER) and Part-of-Speech (POS) tagging tasks. The results reveal that embeddings derived from dynamic models, especially those extracted using the X2Static method, outperform purely static embeddings. Notably, ELMo embeddings achieve the highest accuracy in both NER and POS tagging tasks, underscoring the benefits of contextualized representations even when used in a static form. Our findings highlight the continued relevance of static word embeddings in NLP applications and the potential of advanced extraction methods to enhance the utility of BERT-based models. This piece of research contributes to the understanding of embedding performance in the Hungarian language and provides valuable insights for future developments in the field. The training scripts, evaluation codes, restricted vocabulary, and extracted embeddings will be made publicly available to support further research and reproducibility.

--Despite growing attention to deepfake speech detection, the aspects of bias and fairness remain underexplored in the speech domain. T o address this gap, we introduce the Speaker Characteristics Deepfake (SCDF) dataset: a novel, richly annotated resource enabling systematic evaluation of demographic biases in deepfake speech detection. SCDF contains over 237,000 utterances in a balanced representation of both male and female speakers spanning five languages and a wide age range. We evaluate several state-of-the-art detectors and show that speaker characteristics significantly influence detection performance, revealing disparities across sex, language, age, and synthesizer type. These findings highlight the need for bias-aware development and provide a foundation for building non-discriminatory deepfake detection systems aligned with ethical and regulatory standards.

Scoliosis affects roughly 2 to 4 percent of adolescents, and treatment decisions depend on precise Cobb angle measurement. Manual assessment is time consuming and subject to inter observer variation. We conducted a retrospective, multi centre evaluation of a fully automated deep learning software (Carebot AI Bones, Spine Measurement functionality; Carebot s.r.o.) on 103 standing anteroposterior whole spine radiographs collected from ten hospitals. Two musculoskeletal radiologists independently measured each study and served as reference readers. Agreement between the AI and each radiologist was assessed with Bland Altman analysis, mean absolute error (MAE), root mean squared error (RMSE), Pearson correlation coefficient, and Cohen kappa for four grade severity classification. Against Radiologist 1 the AI achieved an MAE of 3.89 degrees (RMSE 4.77 degrees) with a bias of 0.70 degrees and limits of agreement from minus 8.59 to plus 9.99 degrees. Against Radiologist 2 the AI achieved an MAE of 3.90 degrees (RMSE 5.68 degrees) with a bias of 2.14 degrees and limits from minus 8.23 to plus 12.50 degrees. Pearson correlations were r equals 0.906 and r equals 0.880 (inter reader r equals 0.928), while Cohen kappa for severity grading reached 0.51 and 0.64 (inter reader kappa 0.59). These results demonstrate that the proposed software reproduces expert level Cobb angle measurements and categorical grading across multiple centres, suggesting its utility for streamlining scoliosis reporting and triage in clinical workflows.

This study provides the first comprehensive comparison of New York Times-style text generated by six large language models against real, human-authored NYT writing. The comparison is based on a formal syntactic theory. We use Head-driven Phrase Structure Grammar (HPSG) to analyze the grammatical structure of the texts. We then investigate and illustrate the differences in the distributions of HPSG grammar types, revealing systematic distinctions between human and LLM-generated writing. These findings contribute to a deeper understanding of the syntactic behavior of LLMs as well as humans, within the NYT genre.