Description

Foundation Models (FMs), particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), are gaining significant attention in CPS/IoT research. These models are driving innovative applications across diverse CPS/IoT-related domains, including agriculture, civil infrastructure, healthcare and personalized medicine, manufacturing, and transportation. However, integrating Foundation Models into the CPS/IoT domain presents unique challenges. These include effectively handling multimodal sensing data, real-time operation, optimizing for resource-constrained platforms, and mitigating inference latency. The 2nd International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys) provides a platform for researchers to exchange ideas and share their latest research findings to advance our understanding of Foundation Models in the CPS/IoT community. By fostering research and innovation in these domains, FMSys aims to shape the future trajectory of Foundation Models within the IoT landscape, driving transformative advancements and opening new avenues of exploration. FMSys 2025 is co-located with CPS-IoT Week 2025, the premier venue for research and development of cyber-physical systems.

News

  • 2024.12.13: Web site online

Call for Papers

Foundation Models, particularly Large Language Models (LLMs), have recently garnered significant attention and interest. These models, trained on vast amounts of data, have exhibited remarkable advancements in their ability to generalize across various applications. However, to fully unlock the true potential of Foundation Models, it is crucial to explore and harness their untapped capabilities in real-world systems. While AI/ML researchers have made substantial progress in Foundation Models, the intersection of these models with Cyber-Physical Systems (CPS) and the Internet of Things (IoT) remains largely unexplored. This presents an exciting opportunity to delve into the convergence of CPS/IoT and Foundation Models, unveiling new possibilities, driving technological advancements, and paving the way for seamless integration of intelligent systems within the IoT ecosystem.

In accordance with this objective, the FMSys Workshop provides a timely platform for researchers to exchange ideas and share their latest research findings to advance our understanding of Foundation Models in the CPS/IoT community. FMSys welcomes submissions from researchers from academia and industry that explore the latest developments in this area and encourages encompassing diverse domains, including sensing, systems, security, and applications. By fostering research and innovation in these domains, FMSys aims to shape the future trajectory of Foundation Models within the IoT landscape, driving transformative advancements and opening new avenues of exploration. We will be awarding the best paper at FMSys'25.

Topics of interest include (but are not limited to)


  • Foundation models for CPS/IoT data and applications
    • Foundation models on sensor data analytics, e.g., acoustic, light, motion, RF data
    • Applications of foundation models in healthcare, smart city, virtual reality, social media, etc.
    • Foundation models for reasoning, planning, and control
    • Multimodal foundation models for CPS/IoT
  • New Applications
    • Foundation models for human-computer interaction or human-AI collaboration
    • FM/LLM System as a Service (SaaS) and AI agents
    • FM/LLM-powered Embodied AI systems
  • Datasets and Benchmarks
    • Benchmark evaluations and surveys of foundation models on sensor data
    • CPS/IoT datasets for foundation models
  • Efficiency
    • Efficient fine-tuning of foundation models for CPS/IoT applications
    • Real-time FM/LLM systems for CPS/IoT applications
    • Cloud-edge collaborative inference and training of foundation models
  • Other topics
    • Fairness, trustworthiness, ethics, and security of foundation models
    • Federated learning systems for foundation models

Submission Requirements

Submissions should be original, unpublished research addressing the above topics. Each submission is a single PDF file no longer than six pages (two-column, 10-point, following ACM conference proceedings format (https://www.acm.org/publications/proceedings-template), including figures, references, etc. Submissions must include author names and affiliations for single-blind peer reviewing by the technical program committee. Authors must present their papers in person at the workshop. Papers accepted for presentation will be available at the ACM Digital Library.


Submission Site

TBA, If you have any questions regarding the workshop, please contact TPC chairs. (Mi Zhang, Xiaomin Ouyang )


Important Dates:

  • Paper Registration Deadline: 8 Feb 2025, 11:59 AM UTC
  • Paper Submission Deadline: 15 Feb 2025, 11:59 AM UTC
  • Notification: 13 Mar 2025
  • Camera ready: 20 Mar 2025, 11:59 AM UTC
  • Workshop date: 6 May 2025