Selected work

Representative Papers

On the Multi-Robber Damage Number

Sep 22, 2022arXiv.org

This paper studies a variant of the “Cops and Robbers” game on graphs: $s$ robbers permanently damage vertices they visit, while a single cop aims to prevent such damage. The central question is: for which graph structures can the cop guarantee that at least three vertices remain undamaged? Employing combinatorial game theory, extremal graph theory, and constructive methods, we make three main contributions: (1) We confirm and tighten the three-vertex protection threshold for triangle-free graphs to $inom{s}{2}+2$; (2) We refute a prior conjecture for general graphs and precisely determine the minimum maximum-degree threshold for three-vertex protection within $[2inom{s}{2}-3,, 2inom{s}{2}+1]$; (3) We initiate the first systematic analysis of the two-cops versus two-robbers setting, deriving an exact formula for the number of damaged vertices on cycles and establishing an additive constant error bound on paths.

1 citationsRead paper

A Semantic Communication Approach to Fiducial Marker Processing in 5G-Enabled Edge SLAM

Aug 10, 2026

This work addresses the challenge of achieving efficient communication–perception co-design in 5G-enabled edge SLAM, where conventional fiducial marker detection struggles to balance accuracy and resource constraints. To this end, the paper introduces a semantic segmentation inference framework that, for the first time, integrates semantic communication principles into fiducial processing for edge SLAM. Built upon a DeepTag-inspired CNN, the framework dynamically partitions the model between the robot and an edge server, transmitting task-oriented intermediate semantic features over wireless links to unify communication and perception. Evaluated on a 5G testbed with a ROS2-based robotic platform, the approach demonstrates high-precision keypoint estimation and its positive impact on pose estimation, while also quantifying the communication–computation trade-offs across different model split points, offering practical guidance for deploying visual perception in connected robotic systems.

0 citationsRead paper

Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

Aug 09, 2026

This work addresses the challenge of anomaly detection in decentralized data environments where data cannot be shared across clients. To tackle this issue, the authors propose a federated learning approach that integrates attention mechanisms with autoencoders. The key innovation lies in the design of two novel stochastic aggregation functions specifically tailored for attention-based autoencoders, which effectively preserve critical information from local memory modules on client devices and enhance the global model’s capacity for information integration. Experimental results on the KDDCUP99 dataset demonstrate that the proposed method outperforms conventional autoencoders, achieving relative improvements of 2.9% in F1 score and 5.1% in AUC-ROC, thereby significantly advancing anomaly detection performance in federated settings.

0 citationsRead paper

When One Modality Is Not Enough: Multimodal Sex and Life-Stage Classification of Red Deer from Aerial RGB-Thermal Video

Aug 07, 2026

This study addresses the challenge of accurately classifying red deer by sex and life stage in aerial surveys, where single-modality imagery—either RGB or thermal—is hindered by occlusion, seasonal antler variation, and low resolution. The work presents the first full-stage fusion of RGB and thermal modalities in wildlife aerial census, leveraging self-supervised DINOv3 features for multi-stage modality alignment. It further introduces modality consistency verification and georeferenced body-size calibration, integrated with object tracking and cross-frame voting to jointly infer species, sex, and life stage. Evaluated across four flight campaigns, the method correctly classified 25 out of 26 red deer (96.2%), significantly outperforming single-modality approaches (76.9%) and demonstrating exceptional robustness in sex identification across multiple seasons and complex environmental conditions.

0 citationsRead paper

Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection

Aug 05, 2026

This work addresses the lack of effective aggregation methods for memory-augmented autoencoders (MemAEs) with attention mechanisms in federated learning, which hinders efficient unsupervised anomaly detection under non-IID and resource-constrained settings. To this end, we propose an attention-layer-oriented guided aggregation strategy—the first federated aggregation mechanism specifically designed for MemAEs. Our approach significantly enhances model robustness and detection performance across multiple edge nodes with imbalanced data distributions while maintaining a lightweight architecture. Experimental results demonstrate that the proposed method outperforms existing baselines on various non-IID datasets, achieving higher anomaly detection accuracy and validating the feasibility of shallow MemAEs in edge computing scenarios.

0 citationsRead paper

Recent publications

Latest Papers

A Semantic Communication Approach to Fiducial Marker Processing in 5G-Enabled Edge SLAM

Aug 10, 2026

This work addresses the challenge of achieving efficient communication–perception co-design in 5G-enabled edge SLAM, where conventional fiducial marker detection struggles to balance accuracy and resource constraints. To this end, the paper introduces a semantic segmentation inference framework that, for the first time, integrates semantic communication principles into fiducial processing for edge SLAM. Built upon a DeepTag-inspired CNN, the framework dynamically partitions the model between the robot and an edge server, transmitting task-oriented intermediate semantic features over wireless links to unify communication and perception. Evaluated on a 5G testbed with a ROS2-based robotic platform, the approach demonstrates high-precision keypoint estimation and its positive impact on pose estimation, while also quantifying the communication–computation trade-offs across different model split points, offering practical guidance for deploying visual perception in connected robotic systems.

0 citationsRead paper

Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

Aug 09, 2026

This work addresses the challenge of anomaly detection in decentralized data environments where data cannot be shared across clients. To tackle this issue, the authors propose a federated learning approach that integrates attention mechanisms with autoencoders. The key innovation lies in the design of two novel stochastic aggregation functions specifically tailored for attention-based autoencoders, which effectively preserve critical information from local memory modules on client devices and enhance the global model’s capacity for information integration. Experimental results on the KDDCUP99 dataset demonstrate that the proposed method outperforms conventional autoencoders, achieving relative improvements of 2.9% in F1 score and 5.1% in AUC-ROC, thereby significantly advancing anomaly detection performance in federated settings.

0 citationsRead paper

When One Modality Is Not Enough: Multimodal Sex and Life-Stage Classification of Red Deer from Aerial RGB-Thermal Video

Aug 07, 2026

This study addresses the challenge of accurately classifying red deer by sex and life stage in aerial surveys, where single-modality imagery—either RGB or thermal—is hindered by occlusion, seasonal antler variation, and low resolution. The work presents the first full-stage fusion of RGB and thermal modalities in wildlife aerial census, leveraging self-supervised DINOv3 features for multi-stage modality alignment. It further introduces modality consistency verification and georeferenced body-size calibration, integrated with object tracking and cross-frame voting to jointly infer species, sex, and life stage. Evaluated across four flight campaigns, the method correctly classified 25 out of 26 red deer (96.2%), significantly outperforming single-modality approaches (76.9%) and demonstrating exceptional robustness in sex identification across multiple seasons and complex environmental conditions.

0 citationsRead paper

Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection

Aug 05, 2026

This work addresses the lack of effective aggregation methods for memory-augmented autoencoders (MemAEs) with attention mechanisms in federated learning, which hinders efficient unsupervised anomaly detection under non-IID and resource-constrained settings. To this end, we propose an attention-layer-oriented guided aggregation strategy—the first federated aggregation mechanism specifically designed for MemAEs. Our approach significantly enhances model robustness and detection performance across multiple edge nodes with imbalanced data distributions while maintaining a lightweight architecture. Experimental results demonstrate that the proposed method outperforms existing baselines on various non-IID datasets, achieving higher anomaly detection accuracy and validating the feasibility of shallow MemAEs in edge computing scenarios.

0 citationsRead paper

The Capacity of a Family of Sticky Channels

Jul 30, 2026

This study addresses the Shannon capacity of a class of q-ary sticky insertion channels, wherein symbols are replicated multiple times according to a specific probabilistic rule. By introducing a coefficient dominance condition and leveraging tools from information-theoretic capacity analysis, generating functions, and combinatorics, the authors provide the first exact characterization of the Shannon capacity for this nontrivial replication channel and prove its equivalence to the zero-error capacity. The key contribution lies in constructing an explicit replication law—based on weighted Fuss–Catalan numbers—that satisfies the required conditions, yielding a channel capacity of $\log_2 \lambda$ bits per symbol, where $\lambda$ is uniquely determined by the equation $\lambda^d = (q-1)(\lambda^{d-1} + \cdots + \lambda + 1)$.

0 citationsRead paper