The 3-volume set LNCS 15686 - 15688 constitutes the proceedings of the 19th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2025, which took place in Tokyo, Japan, during June 24-26, 2025. The 70 full papers and 34 short papers included in the proceedings were carefully reviewed and selected from 282 submissions. The proceedings also contain 10 papers from the AICom2 symposium. WASA is a prestigious annual gathering that serves as a global platform for researchers, academics, and industry professionals to explore and exchange  cuttingedge ideas, research findings, and innovative solutions at the dynamic intersection of wireless technologies and artificial intelligence (AI) computing systems.

Table of Contents:
.- A Context-Aware Mental Health LLM Chatbot with Enhanced Security. .- FedTD3: An Accelerated Learning Approach for UAV Trajectory Planning. .- DP-CDA: A Pricing Mechanism for Edge Computing Resources Based on Combinatorial Double Auction and Differential Privacy Preservation. .- Jamming-Resilient Data Aggregation for UAV Ad Hoc Networks. .- Discovering PLC Web Application Vulnerabilities Impacting Physical Control Using LLM-based Fuzzing. .- DSRNet: Hybrid Deep Learning-based Channel Estimation for RIS-Aided Wireless Communication. .- Friend discovery scheme with privacy protection in mobile social networks. .- Channel Selection for EEG Biometrics under Emotion Simulations. .- Intelligent Re-Encryption and Commitment-Driven Dynamic Data Sharing. .- EHFC: Enhanced Format Clustering via Pre-trained Traffic Model. .- High-Precision Ranging Fusion using Neural Network for Bluetooth Channel Sounding. .- Soft Multi-View Representation Learning for Disambiguating Text-based Person Retrieval. .- FedSPA: Federated Learning with Similarity-based Prototype Aggregation. .- Timed and Decentralized Wireless Broadcasting System. .- A High-Performance AI Processor Architecture: Integrating Multi-Controller with Hybrid DDR Memory. .- A DRL-Based Deviation-Aware Federated Digital Twin Construction over Wireless Edge Network. .- SEER: A Slothful Encoding to Mitigate Read Error of Stop-in-Middle Domain-Wall for Reliable Racetrack Memory. .- Breaking the Energy Efficiency-Stability Trade-off: Optimal Lyapunov V Tuning for Wireless-Powered MEC. .- STA-Hyper: Hypergraph-based Spatio-Temporal Attention Network for Next Point-of-Interest Recommendation. .- Generative Adversarial CLIPs for Unsupervised Backlit Image Enhancement. .- MRCC: A Congestion Control Algorithm for Enhanced QoE in Real-Time Networks. .- Privacy-Preserving Credential Management for Blockchain-Based Self-Sovereign Identity. .- Wireless Resource Optimization for UAV Swarm Cooperative Sensing via Multi-Agent Multi-Task Deep Reinforcement Learning. .- A Blockchain-enhanced Hybrid Scheme for Right Registration and Handover. .- Parallelization Techniques for Large Language Models: A Review from Training to Inference. .- DRL-based Computation Offloading and Resource Allocation in THz Band. .- The Defense Against Backdoor Attacks Using Trigger Inversion and Data Augmentation in Clustered Federated Learning. .- ESL-LEO: An Efficient Split Learning Framework over LEO Satellite Networks. .- Accelerating Elliptic Curve Digital Signature verification on FPGA for secure communication. .- Generative Pretrained Transformer for Wireless Traffic Prediction. .- LEO-Integrated Based Partial Task Offloading Optimization in Vehicular Networks. .- Online Personalized Federated Learning Methods for Intrusion Detection in Dynamic UAV Networks. .- Real-Time Reliable Large Language Models with Distributed Knowledge Crowdsourcing for Automotive Mobile Intelligence. .- Adaptive Feature Fusion Enhanced Cascade Pointer Network for Chinese Relation Extraction. .- Quantum Machine Learning: Hybrid System of Quantum and Classical Computing.