Overview

The rapid advancement of ubiquitous sensing has led to an explosion of sensor data across various domains, including smart cities, healthcare, transportation, and environmental monitoring. The emergence of AI models, e.g., Large Language Models (LLMs) and foundation models provides new opportunities for learning from and interacting with sensor data in an adaptive, multi-modal, and intelligent manner. However, these advancements also introduce significant challenges, including the adaptation of LLMs to real-time sensor streams, multimodal data integration, efficient processing on resource-constrained devices, and privacy-aware AI deployment. Organised by a diverse international team of ubicomp researchers, UbiSense 2025 will be hosted at Ubicomp/ISWC 2025 and aims to bring together researchers, practitioners, and industry experts to explore state-ofthe-art AI-driven ubiquitous sensing approaches. We invite novel contributions that address the challenges of applying AI models, including LLMs and foundation models, to sensor data learning, interaction, and decision-making in ubiquitous computing environments.

The Call for Papers is out now! You can find more information here. Accepted papers will be published in the UbiComp/ISWC 2025 Adjunct Proceedings.