2833 papers
This paper presents a lightweight cryptographic heartbeat protocol for robotic swarms that ensures message authentication and integrity in distributed edge-computing systems using only clock synchronization and hash functions, while demonstrating low latency, minimal storage requirements, and robustness against network anomalies on Raspberry Pi 5 hardware.
This paper proposes a privacy-preserving, blockchain-integrated federated learning framework that utilizes NLP and deep learning models, particularly BiLSTM, to detect multilingual cyberbullying in English, Bangla, and Banglish while ensuring data security and user privacy.
This paper introduces LavaCrack_PT, a Transformer-based model that achieves robust 3D crack detection in unstructured lava tube point clouds using LiDAR data from Xianren Cave, providing a validated workflow for structural assessment and future lunar subsurface exploration.
This paper demonstrates that standard higher-order numerical integration schemes often fail to achieve their theoretical asymptotic convergence rates when applied to neural network functions, providing a theoretical error analysis and experimental validation in the context of learning Euler's elastica along with proposed mitigation strategies.
This paper introduces SonoReasoner, an ultrasound vision-language model that enhances diagnostic performance and consistency by explicitly formulating interpretation as hierarchical clinical reasoning, supported by the SonoFlow-1M corpus, the 7-million-scale SonoCorpus reasoning dataset, and the clinician-curated SonoVQA benchmark.
This paper proposes SLS-DNANet, a novel deep learning framework integrating a Multi-Scale Spatial Attention module and a Scale and Location-Sensitive loss function to significantly enhance the detection accuracy and reduce false alarms for small infrared targets with low pixel occupancy and scale variations.
This paper proposes GSE-SFD, a grouped selective federated distillation framework that integrates out-of-distribution filtering, threshold secret sharing, and anomaly detection to simultaneously achieve high accuracy, robustness against client disconnections and poisoning attacks, and enhanced privacy protection in resource-constrained edge environments.
RubriQ is a scalable, HPC-driven framework that leverages rubric-guided Group Relative Policy Optimization (GRPO) to automate the synthesis of quantum circuits that simultaneously satisfy algorithmic correctness, surface-code cost minimization, and near-term hardware constraints.
This paper proposes a method for estimating the complete 3D shape and pose of transparent objects from a single RGB-D image by leveraging YOLO11 for initial detection and iteratively optimizing a category-specific statistical shape model to overcome the limitations of conventional depth sensors.
CAPE-Net is a conformal, adaptive, and drift-aware early-exit classifier that enables ISPs to perform accurate, certified, and maintainable encrypted traffic classification on packet-sequence metadata by integrating distribution-free error guarantees, abstention on unknown applications, and efficient per-class drift repair within a single compact model.