Edge AI Research Symposium 2026: Shaping the Future of Efficient AI Systems

Edge AI San Diego 2026

Edge AI, including Tiny Machine Learning (TinyML), is redefining how intelligence is designed, created, and deployed. Instead of centralising data and computation in the cloud, Edge AI brings machine learning directly onto local devices near the data sources.This decentralised approach improves latency, privacy, and resilience while reducing network and energy costs.

The field is advancing rapidly through research and industrial innovation across multiple dimensions:

• Real-world deployment of low-power vision, audio, and multimodal systems
• Innovation in GenAI@Edge and small language models
• New architectures and topologies for distributed and federated learning
• Algorithms and models scaled to sub-100 kB footprints
• Co-design of hardware, firmware, and software for real-time operation
• Communication frameworks for efficient model exchange and synchronisation

The Edge AI Research Symposium serves as a leading technical forum for research that advances decentralised and distributed intelligence at the edge.It brings together researchers and practitioners working on embedded machine learning, system optimisation, and hardware innovation.

Held in conjunction with the Edge AI Summit, this symposium unites experts from academia and industry to explore the next generation of machine learning at the edge of the network.

Important Dates

• Submission Deadline: 15 December 2025
• Notification of Acceptance: 9 January 2026

Submissions should integrate concepts or techniques from at least two subject areas listed below.Accepted full papers will be published in IEEE Pervasive Computing (Q3 & Q4, 2026).

Details for submission through the official portal will be announced soon.At least one author of each accepted paper must attend the symposium in person to present.

Technical Areas of Interest

• Edge AI Datasets: Public datasets for embedded learning; frameworks for automated data collection and annotation; dataset adaptation for distributed environments; surveys of lightweight datasets for embedded inference.
• Edge AI Applications: Deployment case studies in healthcare, manufacturing, transportation, and environmental monitoring; user–system interaction in decentralised networks; validation and benchmarking of field systems.
• Edge AI Algorithms: Algorithms for resource-constrained and distributed environments; quantisation, pruning, and compression; continual and federated learning; lightweight privacy-preserving methods; adaptive and communication-efficient learning.
• Edge AI Systems: System-level design for low-latency, high-efficiency inference; profiling tools for performance and power analysis; hardware–software co-design; near-sensor computing; hybrid architectures combining edge and cloud.
• Edge AI Software: Lightweight execution frameworks and interpreters; compiler optimisations for limited-memory devices; distributed runtime systems; software for model partitioning and synchronisation in multi-node environments.
• Edge AI Hardware: Architectures and circuits for decentralised inference; near-memory and in-memory computing; low-power accelerators; microcontroller design; hardware mechanisms for security, reliability, and adaptive power control.
• Evaluation and Benchmarking: Tools for reproducible measurement of performance, latency, and power; frameworks for evaluating distributed learning systems; analysis of scalability and robustness in real deployments.
• Distributed and Collaborative Edge AI: Architectures for peer-to-peer and federated learning; cooperative decision-making; asynchronous model updates; communication protocols for edge-to-edge and edge-to-cloud coordination.
• Generative AI and Small Language Models: Design and optimisation of generative and language models for constrained environments; compression and adaptation techniques for edge deployment; privacy and safety in on-device generative systems.

Symposium Chairs

Chair: Prof. Tinoosh Mohsenin, Johns Hopkins UniversityCo-Chair: Prof Eiman Kanjo, Nottingham Trent University and Imperial College London

Prof. Tinoosh Mohsenin is an Associate Professor of Electrical and Computer Engineering and Computer Science at Johns Hopkins University, where she directs the Energy-Efficient High-Performance Computing (EEHPC) Lab. She has authored over 150 peer-reviewed publications and is a recipient of the NSF CAREER Award, as well as Best Paper Awards at the AAAI Spring Symposium GenAI@Edge (2025), ACM Great Lakes VLSI Conference (2016), and IEEE Circuits and Systems Symposium (2017) for her contributions to biomedical and deep learning processors. Dr. Mohsenin has received ACM Service Awards for her leadership as General Chair (2020) and Program Chair (2019) of the ACM Great Lakes VLSI Symposium, as well as the ISSCC Evening Session Award (2020). She serves on the Senior Editorial Board of IEEE JETCAS and has held several leadership roles, including Chair and Organizer of the AAAI Spring Symposium GenAI@Edge (2025), Co-Chair and Organizer of the 60th and 61st IEEE/ACM DAC Workshops on Deep Learning Hardware Co-Design for Generative AI Acceleration, and Co-Chair of the Edge AI Foundation in Academia. She has also been a keynote speaker at several renowned IEEE conferences, including AICAS, ICECS, DCAS, and PerCONAI.

Prof. Eiman Kanjo is Professor of TinyML and Head of the Smart Sensing Lab at Nottingham Trent University. She is Honorary Visiting Professor in the Department of Computing at Imperial College London, where she previously held the Provost’s Visiting Professorship in Pervasive Sensing and TinyML. She is Director of the EPSRC Green+ Network and Director of the upcoming TinyML UK Network . She is currently a co-lead on the EPSRC Prosensing project with the University of Edinburgh and Strathclyde university . She was named one of the Top 50 Women in Engineering by the Women in Engineering Society. She is the Turing University Network Academic Lead at the Alan Turing Institute and received the Turing Network Development Award in 2022. She has published more than 150 research papers and has secured funding from EPSRC, DCMS, Innovate UK, the EU, DSTL, ERDF, MoD, and the Lottery Fund. She received the EdgeAI Foundation Outstanding Educator Award in 2025.  She serves as Associate Director at Health Data Research UK HDRUK Midlands, and she chaired the 2025 annual HDRUK  Midlands conference with focus on AI on Wearables.  Earlier in her career, she was worked at the University of Cambridge and the University of Nottingham.