The six-volume proceedings set LNAI 15919, 15920, 15921, 15922, 15923 and 15924 constitutes the refereed proceedings of the 18th International Conference on Knowledge Science, Engineering and Management, KSEM 2025, held in Macao, China during August 4–7, 2025.
The 106 papers and 66 short papers are included in these proceedings were carefully reviewed and selected from 354 submissions. They focus on all aspects of the exchange of research in artificial intelligence, data science, knowledge engineering, AI safety, large language models, and related frontier areas.
.- ACL:Adaptive Chunking of Large Language Models for Efficient Inference on Automotive Edge Devices.
.- The Evaluation of Parameter-agnostic Unlearning Mechanisms on Prevailing Large Language Models.
.- Node Centrality Approximation in Complex Networks via Inductive Graph Neural Networks.
.- Carbon Market Price Prediction Method Based on Multi-feature Fusion and Deep Learning.
.- MMtuning: An Advanced Multi-Adapter Framework for Efficient Multimodal Large Language Models Fine-Tuning.
.- Multi-Sensor Fusion Framework for HAR: Integrating Time-Frequency Features and Self-Supervised Learning.
.- Deep Reinforcement Learning-Based Client Selection and Secure Aggregation for Federated Learning.
.- DynamicFedPEFT: Efficient fine-tuning of dynamic federated parameters for l.