Special Session on LLM-IoT (LLM-IoT)

Scope

The Internet of Things (IoT) has experienced rapid growth in recent years, generating widespread interest in domains such as smart cities, healthcare, industrial systems, and wearable devices. The increasing ubiquity of connected sensors and actuators has led to unprecedented volumes of heterogeneous data, demanding more intelligent, adaptive, and human-centered ways of managing and exploiting this information. In parallel, Large Language Models (LLMs) have emerged as a prominent development in Artificial Intelligence (AI), enabling users to interact with computer systems through natural language and offering new capabilities in understanding, summarizing, and reasoning complex data.

The convergence of IoT and LLMs represents a natural next step in the evolution of intelligent environments. LLMs can serve as an interpretative and interaction layer on top of IoT infrastructures, transforming raw, low-level signals into higher-level, context-aware insights accessible to non-expert users. This opens the door to more intuitive interfaces, proactive decision support, and automated control mechanisms better aligned with human needs and expectations. At the same time, this integration raises important challenges related to resource constraints at the edge, data privacy and security, robustness, explainability, and the alignment of LLM-driven behaviors with domain-specific requirements and regulations.

---

---

---

Topics

• Novel architectures for deploying LLM in edge and resource-constrained environments.
• Comparative assessments of LLM-based solutions versus traditional machine learning and heuristic approaches.
• Enhancing scalability, robustness, and computational efficiency of IoT-data processing through LLM.
• New frameworks for the integration of IoT ecosystems with LLM.
• Methodologies for the analysis and interpretation of complex IoT data streams.
• Generating coherent, human-understandable information from raw sensor data.
• LLM-driven tools for supporting individual and organizational decision processes.
• Development of standardized benchmarks for assessing LLM performance in IoT contexts.
• Solutions for secure data handling and anonymization in IoT with LLM.
• Addressing security vulnerabilities in automated interpretation and decision-making.
• Ensuring fairness and transparency in autonomous IoT systems.
• Applications in Smart Cities, Transport, and Agriculture.
• LLM integration in manufacturing and industrial automation.
• Solutions for Healthcare, Ambient Assisted Living, and remote monitoring.¡