AutoMLPerSys is focused on enhancing and nurturing research in the niche domain of AutoML for tiny edge systems like wearables/implantable and smart fabrics, that perform pervasive human sensing. We welcome full papers (up to 6 pages) with novel ideas on the automation of machine learning for pervasive sensing applications. Submissions can be in research areas including, but not limited to the following:
AutoML for Human Sensing.
Hyperparameter Optimization Techniques, Neural Architecture Search Techniques for resource-constrained platforms
Methods and challenges in the implementation of AutoML-generated models on Wearable, Implantable, Smart Fabrics and Mobile Devices, including Connected Home and Connected Vehicle Edge Devices.
Open Datasets with initial benchmarking results for AutoML research.
Real-time parameters and their optimization and impact on on-device inference.
Addressing issues related to devising Deployment and Inference, such as Data Quality, Resource Constraints, Interpretability, Feature Engineering, Privacy and Sustainability
Addressing problems arising due to model parameter reduction, such as Robustness, Personalization and Generalizability, Reliability and Scalability
Application-specific deployment of AI on edge devices impacts the various user privacy and feasibility concerns and sustainability in short-term as well as long-term.
The various challenges involved in making a model architecture fit for pervasive usage - whether the reduction in size and parameters results in a fair trade-off between resource demand and metrics (Accuracy, Robustness).
The right balance between the cost of resources (Power, GPU hours, Memory usage) to automate the model design and reduction process vs. the benefits achieved in terms of tiny model architectures with low resource footprint for training and inference for continuously running applications.
Energy consideration and Power budgeting for continuous Sensing and Inference.
Submission Instructions
All papers must be at most 6 pages of technical content, typeset in double-column IEEE format using 10pt fonts on US letter paper, with all fonts embedded. In AutoMLPerSys 2026, the peer-review process will be single-blind. Papers should contain names and affiliations of the authors.
Submissions must be made via EDAS. The IEEE LaTeX and Microsoft Word templates and related information can be found on the IEEE Computer Society website.
AutoMLPerSys 2026 will be held in conjunction with IEEE PerCom 2026 (https://www.percom.org). All accepted papers will be included in the Percom workshop proceedings and indexed in the IEEEXplore digital library subject to the IEEE and PerCom 2026.
At least one author must register for the conference in full and present the paper during the workshop physically. Papers without a valid full registration or that are not presented in-person will be excluded from the proceedings.
Workshop papers must adhere to the standard length limit: 6 pages, with the option to include 1 additional page for a maximum of 7 pages total.
Workshop presentations—including papers, keynotes, and invited talks—must be delivered in person by a designated presenter, preferably one of the authors in the case of papers. Proxy or remote presentations are not allowed unless pre-approved by the workshop chairs, general chairs, and the steering committee at least one week in advance.
Paper Submission Link: https://edas.info/N34011
Important Dates:
Paper Submission Deadline: November 17, 2025
Acceptance Notification: January 05, 2026
Author Registration deadline: TBA
Camera-ready Submission: February 02, 2026 (Firm deadline)
Workshop date: TBA
For queries related to AutoMLPerSys 2026, please write to automlpersys.chairs@gmail.com