Automated polyp counting in colonoscopy is a crucial step toward automated procedure reporting and quality control, aiming to enhance the cost-effectiveness of colonoscopy screening. Counting polyps in a procedure involves detecting and tracking polyps, and then clustering tracklets that belong to the same polyp entity. Existing methods for polyp counting rely on self-supervised learning and primarily leverage visual appearance, neglecting temporal relationships in both tracklet feature learning and clustering stages. In this work, we introduce a paradigm shift by proposing a supervised contrastive loss that incorporates temporally-aware soft targets. Our approach captures intra-polyp variability while preserving inter-polyp discriminability, leading to more robust clustering. Additionally, we improve tracklet clustering by integrating a temporal adjacency constraint, reducing false positive re-associations between visually similar but temporally distant tracklets. We train and validate our method on publicly available datasets and evaluate its performance with a leave-one-out cross-validation strategy. Results demonstrate a 2.2x reduction in fragmentation rate compared to prior approaches. Our results highlight the importance of temporal awareness in polyp counting, establishing a new state-of-the-art. Code is available at https://github.com/lparolari/temporally-aware-polyp-counting.

In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard proprietary models hinder practical implementation. To address this issue, we introduce a novel late collaborative framework for 3D multi-source and multi-object fusion, which operates solely on shared 3D bounding box attributes-category, size, position, and orientation-without necessitating direct access to detection models. Our framework establishes a new state-of-the-art in late fusion, achieving up to five times lower position error compared to existing methods. Additionally, it reduces scale error by a factor of 7.5 and orientation error by half, all while maintaining perfect 100% precision and recall when fusing detections from heterogeneous perception systems. These results highlight the effectiveness of our approach in addressing real-world collaborative perception challenges, setting a new benchmark for efficient and scalable multi-agent fusion.

Modern vehicles are increasingly connected, and in this context, automotive Ethernet is one of the technologies that promise to provide the necessary infrastructure for intra-vehicle communication. However, these systems are subject to attacks that can compromise safety, including flow injection attacks. Deep Learning-based Intrusion Detection Systems (IDS) are often designed to combat this problem, but they require expensive hardware to run in real time. In this work, we propose to evaluate and apply fast neural network inference techniques like Distilling and Prunning for deploying IDS models on low-cost platforms in real time. The results show that these techniques can achieve intrusion detection times of up to 727 μs using a Raspberry Pi 4, with AUCROC values of 0.9890.

Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), an intelligent platform that integrates LLMs, VLMs, and modular robotics to autonomously design, plan, and execute biological experiments. BioMARS uses a hierarchical architecture: the Biologist Agent synthesizes protocols via retrieval-augmented generation; the Technician Agent translates them into executable robotic pseudo-code; and the Inspector Agent ensures procedural integrity through multimodal perception and anomaly detection. The system autonomously conducts cell passaging and culture tasks, matching or exceeding manual performance in viability, consistency, and morphological integrity. It also supports context-aware optimization, outperforming conventional strategies in differentiating retinal pigment epithelial cells. A web interface enables real-time human-AI collaboration, while a modular backend allows scalable integration with laboratory hardware. These results highlight the feasibility of generalizable, AI-driven laboratory automation and the transformative role of language-based reasoning in biological research.

We present a full-stack emergency vehicle (EV) siren detection system designed for real-time deployment on embedded hardware. The proposed approach is based on E2PANNs, a fine-tuned convolutional neural network derived from EPANNs, and optimized for binary sound event detection under urban acoustic conditions. A key contribution is the creation of curated and semantically structured datasets - AudioSet-EV, AudioSet-EV Augmented, and Unified-EV - developed using a custom AudioSet-Tools framework to overcome the low reliability of standard AudioSet annotations. The system is deployed on a Raspberry Pi 5 equipped with a high-fidelity DAC+microphone board, implementing a multithreaded inference engine with adaptive frame sizing, probability smoothing, and a decision-state machine to control false positive activations. A remote WebSocket interface provides real-time monitoring and facilitates live demonstration capabilities. Performance is evaluated using both framewise and event-based metrics across multiple configurations. Results show the system achieves low-latency detection with improved robustness under realistic audio conditions. This work demonstrates the feasibility of deploying IoS-compatible SED solutions that can form distributed acoustic monitoring networks, enabling collaborative emergency vehicle tracking across smart city infrastructures through WebSocket connectivity on low-cost edge devices.

To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained on in-distribution data. In this paper, we critically re-examine this popular family of OOD detection procedures, and we argue that these methods are fundamentally answering the wrong questions for OOD detection. There is no simple fix to this misalignment, since a classifier trained only on in-distribution classes cannot be expected to identify OOD points; for instance, a cat-dog classifier may confidently misclassify an airplane if it contains features that distinguish cats from dogs, despite generally appearing nothing alike. We find that uncertainty-based methods incorrectly conflate high uncertainty with being OOD, while feature-based methods incorrectly conflate far feature-space distance with being OOD. We show how these pathologies manifest as irreducible errors in OOD detection and identify common settings where these methods are ineffective. Additionally, interventions to improve OOD detection such as feature-logit hybrid methods, scaling of model and data size, epistemic uncertainty representation, and outlier exposure also fail to address this fundamental misalignment in objectives. We additionally consider unsupervised density estimation and generative models for OOD detection, which we show have their own fundamental limitations.

Graphical models have been popularly used for capturing conditional independence structure in multivariate data, which are often built upon independent and identically distributed observations, limiting their applicability to complex datasets such as network-linked data. This paper proposes a nonparametric graphical model that addresses these limitations by accommodating heterogeneous graph structures without imposing any specific distributional assumptions. The proposed estimation method effectively integrates network embedding with nonparametric graphical model estimation. It further transforms the graph learning task into solving a finite-dimensional linear equation system by leveraging the properties of vector-valued reproducing kernel Hilbert space. Moreover, theoretical guarantees are established for the proposed method in terms of the estimation consistency and exact recovery of the heterogeneous graph structures. Its effectiveness is also demonstrated through a variety of simulated examples and a real application to the statistician coauthorship dataset.

Background and Objective: High-throughput multi-omics technologies have proven invaluable for elucidating disease mechanisms and enabling early diagnosis. However, the high cost of multi-omics profiling imposes a significant economic burden, with over reliance on full omics data potentially leading to unnecessary resource consumption. To address these issues, we propose an uncertainty-aware, multi-view dynamic decision framework for omics data classification that aims to achieve high diagnostic accuracy while minimizing testing costs. Methodology: At the single-omics level, we refine the activation functions of neural networks to generate Dirichlet distribution parameters, utilizing subjective logic to quantify both the belief masses and uncertainty mass of classification results. Belief mass reflects the support of a specific omics modality for a disease class, while the uncertainty parameter captures limitations in data quality and model discriminability, providing a more trustworthy basis for decision-making. At the multi omics level, we employ a fusion strategy based on Dempster-Shafer theory to integrate heterogeneous modalities, leveraging their complementarity to boost diagnostic accuracy and robustness. A dynamic decision mechanism is then applied that omics data are incrementally introduced for each patient until either all data sources are utilized or the model confidence exceeds a predefined threshold, potentially before all data sources are utilized. Results and Conclusion: We evaluate our approach on four benchmark multi-omics datasets, ROSMAP, LGG, BRCA, and KIPAN. In three datasets, over 50% of cases achieved accurate classification using a single omics modality, effectively reducing redundant testing. Meanwhile, our method maintains diagnostic performance comparable to full-omics models and preserves essential biological insights.

In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Transformer attention rollout into a unified visualization, achieving full spatial-temporal alignment while preserving real-time performance. Empirical evaluations on clinical (ECG arrhythmia detection) and industrial (energy consumption prediction) datasets demonstrate significant improvements: the hybrid framework achieves 94.1% accuracy (F1 0.93) on the PhysioNet dataset and reduces regression error to RMSE = 0.28 kWh (R2 = 0.95) on the UCI Energy Appliance dataset-outperforming standalone ResNet, Transformer, and InceptionTime baselines by 3.8-12.4%. An NLP module translates fused heatmaps into domain-specific narratives (e.g., "Elevated ST-segment between 2-4 seconds suggests myocardial ischemia"), validated via BLEU-4 (0.586) and ROUGE-L (0.650) scores. By formalizing interpretability as causal fidelity and spatial-temporal alignment, our approach bridges the gap between technical outputs and stakeholder understanding, offering a scalable solution for transparent, time-aware decision-making.

Abstract: We utilize dynamical modes as features derived from Continuous Glucose Monitoring (CGM) data to detect meal events. By leveraging the inherent properties of underlying dynamics, these modes capture key aspects of glucose variability, enabling the identification of patterns and anomalies associated with meal consumption. This approach not only improves the accuracy of meal detection but also enhances the interpretability of the underlying glucose dynamics. By focusing on dynamical features, our method provides a robust framework for feature extraction, facilitating generalization across diverse datasets and ensuring reliable performance in real-world applications. The proposed technique offers significant advantages over traditional approaches, improving detection accuracy, detection delay, and system robustness.