ABSTRACT Consistency regularization (CR), which enforces agreement between model predictions on augmented views, has found recent benefits in automatic speech recognition [1]. In this paper, we propose the use of consistency regularization for audio event recognition, and demonstrate its effectiveness on AudioSet. With extensive ablation studies for both small ( 20k) and large ( 1.8M) supervised training sets, we show that CR brings consistent improvement over supervised baselines which already heavily utilize data augmentation, and CR using stronger augmentation and multiple augmentations leads to additional gain for the small training set. Furthermore, we extend the use of CR into the semi-supervised setup with 20K labeled samples and 1.8M unlabeled samples, and obtain performance improvement over our best model trained on the small set. Index T erms-- Audio event recognition, consistency regularization, data augmentation 1. INTRODUCTION Audio Event Recognition (AER) plays a major role in real-world systems, such as wearable devices [2], smart home devices [3], surveillance systems [4-6], and human activity [7, 8].

We present a machine learning framework for adaptive source localization in which agents use a structure-preserving digital twin of a coupled hydrodynamic-transport system for real-time trajectory planning and data assimilation. The twin is constructed with conditional neural Whitney forms (CNWF), coupling the numerical guarantees of finite element exterior calculus (FEEC) with transformer-based operator learning. The resulting model preserves discrete conservation, and adapts in real time to streaming sensor data. It employs a conditional attention mechanism to identify: a reduced Whitney-form basis; reduced integral balance equations; and a source field, each compatible with given sensor measurements. The induced reduced-order environmental model retains the stability and consistency of standard finite-element simulation, yielding a physically realizable, regular mapping from sensor data to the source field. We propose a staggered scheme that alternates between evaluating the digital twin and applying Lloyd's algorithm to guide sensor placement, with analysis providing conditions for monotone improvement of a coverage functional. Using the predicted source field as an importance function within an optimal-recovery scheme, we demonstrate recovery of point sources under continuity assumptions, highlighting the role of regularity as a sufficient condition for localization. Experimental comparisons with physics-agnostic transformer architectures show improved accuracy in complex geometries when physical constraints are enforced, indicating that structure preservation provides an effective inductive bias for source identification.

Overconfidence in deep learning models poses a significant risk in high - stakes medical imaging tasks, particularly in multi - label classification of chest X - rays, where multiple co - occurring pathologies must be detected simultaneously. This study introduces an uncertainty - aware framework for chest X - ray diagnosis based on a DenseNet - 121 backbone, enhanced with two selective prediction mechanisms: entropy - based rejection and confidence interval - based rejection. Both methods enable the model to abstain from un certain predictions, improving reliability by deferring ambiguous cases to clinical experts. A quantile - based calibration procedure is employed to tune rejection thresholds using either global or class - specific strategies. Experiments conducted on three la rge public datasets (PadChest, NIH ChestX - ray14, and MIMIC - CXR) demonstrate that selective rejection improves the trade - off between diagnostic accuracy and coverage, with entropy - based rejection yielding the highest average A U C across all pathologies. Thes e results support the integration of selective prediction into AI - assisted diagnostic workflows, providing a practical step toward safer, uncertainty - aware deployment of deep learning in clinical settings. Automating medical diagnosis with deep learning has shown great potential, particularly in medical imaging domains such as chest X - ray analysis. Convolutional neural networks, including architectures like DenseNet - 121, have demonstrated strong performance in detecting a range of thoracic pathologies [1],[2] . However, successfully integrating such models into clinical workflows requires more than high classification accuracy . I t demands robust mechanisms for managing uncertainty and ensuring patient safety. 2 Figure 1: Overview of the proposed selective chest X - ray classification framework .

Mammography screening is an essential tool for early detection of breast cancer. The speed and accuracy of mammography interpretation have the potential to be improved with deep learning methods. However, the development of a foundation visual language model (VLM) is hindered by limited data and domain differences between natural and medical images. Existing mammography VLMs, adapted from natural images, often ignore domain-specific characteristics, such as multi-view relationships in mammography. Unlike radiologists who analyze both views together to process ipsilateral correspondence, current methods treat them as independent images or do not properly model the multi-view correspondence learning, losing critical geometric context and resulting in suboptimal prediction. We propose GLAM: Global and Local Alignment for Multi-view mammography for VLM pretraining using geometry guidance. By leveraging the prior knowledge about the multi-view imaging process of mammograms, our model learns local cross-view alignments and fine-grained local features through joint global and local, visual-visual, and visual-language contrastive learning. Pretrained on EMBED [14], one of the largest open mammography datasets, our model outperforms baselines across multiple datasets under different settings.

Recent advances in Language Models (LMs) have failed to mask their shortcomings particularly in the domain of reasoning. This limitation impacts several tasks, most notably those involving ontology engineering. As part of a PhD research, we investigate the consequences of incorporating formal methods on the performance of Small Language Models (SLMs) on reasoning tasks. Specifically, we aim to orient our work toward using SLMs to bootstrap ontology construction and set up a series of preliminary experiments to determine the impact of expressing logical problems with different grammars on the performance of SLMs on a predefined reasoning task. Our findings show that it is possible to substitute Natural Language (NL) with a more compact logical language while maintaining a strong performance on reasoning tasks and hope to use these results to further refine the role of SLMs in ontology engineering.

Recommender systems often benefit from complex feature embeddings and deep learning algorithms, which deliver sophisticated recommendations that enhance user experience, engagement, and revenue. However, these methods frequently reduce the interpretability and transparency of the system. In this research, we develop a systematic application, adaptation, and evaluation of deletion diagnostics in the recommender setting. The method compares the performance of a model to that of a similar model trained without a specific user or item, allowing us to quantify how that observation influences the recommender, either positively or negatively. To demonstrate its model-agnostic nature, the proposal is applied to both Neural Collaborative Filtering (NCF), a widely used deep learning-based recommender, and Singular Value Decomposition (SVD), a classical collaborative filtering technique. Experiments on the MovieLens and Amazon Reviews datasets provide insights into model behavior and highlight the generality of the approach across different recommendation paradigms.

Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we propose a novel self improving framework,Self Improving Faithfulness Aware Contrastive Tuning.The framework uses a self instruct mechanism that allows the base LLM to automatically generate high quality,structured contrastive learning data,including anchor samples,semantically equivalent positive samples,and negative samples simulating unfaithful scenarios.This approach significantly reduces the cost of manual annotation.Subsequently,contrastive learning is applied to train the model,enabling it to pull faithful responses closer and push unfaithful responses farther apart in the representation space.Experiments on knowledge conflict evaluation benchmarks ECARE KRE and COSE KRE show that the SI FACT model based on Llama3 8B Instruct improves the Contextual Recall Rate by 6.2% over the best baseline method,while significantly reducing dependence on internal memory.The results indicate that SI FACT provides strong effectiveness and high data efficiency in enhancing the contextual faithfulness of LLMs,offering a practical pathway toward building more proactive and trustworthy language models.

With the rise of fifth-generation (5G) networks in critical applications, it is urgent to move from detection of malicious activity to systems capable of providing a reliable verdict suitable for mitigation. In this regard, understanding and interpreting machine learning (ML) models' security alerts is crucial for enabling actionable incident response orchestration. Explainable Artificial Intelligence (XAI) techniques are expected to enhance trust by providing insights into why alerts are raised. A dominant approach statistically associates feature sets that can be correlated to a given alert. This paper starts by questioning whether such attribution is relevant for future generation communication systems, and investigates its merits in comparison with an approach based on logical explanations. We extensively study two methods, SHAP and VoTE-XAI, by analyzing their interpretations of alerts generated by an XGBoost model in three different use cases with several 5G communication attacks. We identify three metrics for assessing explanations: sparsity, how concise they are; stability, how consistent they are across samples from the same attack type; and efficiency, how fast an explanation is generated. As an example, in a 5G network with 92 features, 6 were deemed important by VoTE-XAI for a Denial of Service (DoS) variant, ICMPFlood, while SHAP identified over 20. More importantly, we found a significant divergence between features selected by SHAP and VoTE-XAI. However, none of the top-ranked features selected by SHAP were missed by VoTE-XAI. When it comes to efficiency of providing interpretations, we found that VoTE-XAI is significantly more responsive, e.g. it provides a single explanation in under 0.002 seconds, in a high-dimensional setting (478 features).

Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised learning, which achieves the best BenchECG score compared to publicly available state-of-the-art models. In particular, xECG is the only publicly available model to perform strongly on all datasets and tasks. By standardising evaluation, BenchECG enables rigorous comparison and aims to accelerate progress in ECG representation learning. xECG achieves superior performance over earlier approaches, defining a new baseline for future ECG foundation models.

The rapid adoption of autonomous AI agents is giving rise to a new economic layer where agents transact and coordinate at scales and speeds beyond direct human oversight. We propose the "sandbox economy" as a framework for analyzing this emergent system, characterizing it along two key dimensions: its origins (emergent vs. intentional) and its degree of separateness from the established human economy (permeable vs. impermeable). Our current trajectory points toward a spontaneous emergence of a vast and highly permeable AI agent economy, presenting us with opportunities for an unprecedented degree of coordination as well as significant challenges, including systemic economic risk and exacerbated inequality. Here we discuss a number of possible design choices that may lead to safely steerable AI agent markets. In particular, we consider auction mechanisms for fair resource allocation and preference resolution, the design of AI "mission economies" to coordinate around achieving collective goals, and socio-technical infrastructure needed to ensure trust, safety, and accountability. By doing this, we argue for the proactive design of steerable agent markets to ensure the coming technological shift aligns with humanity's long-term collective flourishing.