Network and Parallel Computing: 21st IFIP WG 10.3 International Conference, NPC 2025, Nha Trang, Vietnam, November 14–16, 2025, Proceedings, Part II(16306 Lecture Notes in Computer Science)

This two-part volume LNCS 16305 and 16306 constitutes the proceedings of the 21st IFIP International Conference on Network and Parallel Computing, NPC 2025, which was held in Nha Trang, Vietnam, during November 14-16, 2025. The 76 full papers included in this volume were carefully reviewed and selected from 223 submissions. Topics of interest include, but are not limited to, parallel and distributed applications and algorithms, parallel and distributed architectures and systems, and parallel and distributed software environments and tools.

Table of Contents:
.- Dynamic Resource Allocation with Adaptive Mode Selection in D2D-V2X Networks. .- A Digital Twin-Assisted Multi-Agent Task Offloading Method with Priority Scheduling in Vehicular Edge Networks. .- DDPG-Based Joint Dynamic Task Offloading and Resource Allocation for Multi-User MEC Networks. .- CGO: Cloud Game Orchestration via Resource Preception and CODEC Optimization. .- Role-Aware Dynamic Grouping for Efficient Coordination in Multi-Agent Reinforcement Learning. .- SynergiCache: A Novel Cluster Cache for Enhancing Performance in Cloud Storage Systems. .- Image Compressive Sensing Approach Based on Mixed Precision Training and Deep Unrolling Network. .- FastDAG: A Low-Latency and Parallel Wave-Execution Consensus with a Double-Layer DAG. .- Long-term Cloud Workload Prediction with Multi-period Augmented LSTM. .- In-Orbit Container Registry Planning for Fast Image Downloading in LEO Satellite Constellation. .- TIDF: Timing-based Device Fingerprinting for PLCs. .- Deadlock-Free Transaction Processing in Payment Channel Networks. .- QoSmart-IoT: Secure QoS-Based Reconfiguration and Protocol Adaptation for Hybrid Clustered IoT Systems in Constrained Environments. .- ManuMatic: Strategy Injection for Robust Automatic Hybrid Parallelism in Distributed DNN Training. .- Maximizing the Utility of Multiple UAV Service Providers: A Hierarchical Cooperation Approach. .- Slotqueue: A Wait-Free Distributed Multi-Producer Single-Consumer Queue with Constant Remote Operations. .- Exploiting Hard Samples for Stealthy Backdoor Attacks on Large Language Models. .- FedSM: A Federated Spectrum Management Architecture for 6G Network. .- TriCooling-Sim: Efficient Thermal Simulation for High-Density Micro AI Data Centers. .- Semantic-Driven Task-Traffic Co-Scheduling for TSN with Generalization Ability: A Heterogeneous Graph Neural Network-based Method. .- CPU-GPU Heterogeneity Based Pipeline Parallel Architecture in Physical Layer Processing. .- HBD-CE: Efficient Cross-HBD Communication for LLM Training in High-Bandwidth Domain Cluster via Hierarchical Collectives. .- NNia-8: An 8-Core RISC-V Neural Network Inference Accelerator with Efficient Processing Elements and Memory Utilization. .- GPowerT: LLM-Driven Automated Programming for Power-Constrained IoT Applications. .- Millisecond-level Interference-aware Scheduling for Multi-inference Co-location on Ascend NPUs. .- An Unsupervised Learning Log Anomaly Detection Method Based on Graph Neural Network. .- Adaptive Reed-Solomon Coding for OFDM in Mobile Visible Light Communications. .- Fast and Accurate RDMA Congestion Control with Self-Adapting Rate Adjustment. .- Age of Information Minimization for Secure and Covert UAV communications. .- LGSVE: Leader-Guided Soft Voting Ensemble Model for Class-Imbalanced IoT Intrusion Detection. .- LLM-Guided Soft Actor-Critic for Resource Allocation in Mobile Edge Computing Networks. .- ASALP: An Automatic Scaling Architecture for Edge Node Resources Based on Load Prediction. .- CRANE: Two-Stage Coordinated Resource Allocation of Network and Compute for Deterministic Workloads. .- Federated Learning via TEE-Based Dual-Branch Architecture and Interaction-Aware Pruning. .- Breaking Language Barriers : A Domain-Specific Translation Workflow for Industry. .- PHITS: A Parallel Hyperlink - Induced Topic Search Algorithm with Graph Partitioning and Communication Optimization. .- Reducing Load-balancing Cost on Asymmetric NUMA Machine. .- Data Plane Driven Adaptive Routing with In-Network Reinforcement Learning.