Tiny machine learning (tinyML) is a fast-growing field of machine learning technologies enabling on-device sensor data processing at extremely low power, typically in the milliwatt range and below. The tinyML ecosystem is fueled by (i) current applications in vision and audio that are already becoming mainstream and commercially available; (ii) emerging low-power commercial applications and new system concepts on the horizon; (iii) significant progress on algorithms, networks, and models down to 100 kB and below; and (iv) optimized hardware platforms, processor architectures and circuit concepts for extreme energy efficiency and hard real-time operation. There is growing momentum demonstrated by technical progress and ecosystem development in all of these areas. The tinyML research symposium serves as a flagship venue for related research at the intersection of machine learning applications, algorithms, software, and hardware in deeply embedded machine learning systems.

The tinyML Research Symposium is held in conjunction with the tinyML Summit, the premier annual gathering of senior level technical experts and decision makers representing the global tinyML community.

Call for papers


Deadline Extended till Monday Dec 9, 2024, 12 PM EST


The 5th edition of the tinyML Research Symposium now called EDGE AI Research Track 2025 will take place as as an integrated part of the EDGE AI FOUNDATION’s Austin 2025 event taking place at the Assembly Hall Austin, 1121 East 7th Street, Austin, TX 78702 from February 25-27, 2025. We solicit papers from academia and industry that emphasize cross-layer innovation in the field of Edge AI and tinyML and variants of AI in resource constrained environments * We solicit papers from academia and industry that emphasize cross-layer innovation in the field of tinyML * Submissions must intersect and leverage synergy between at least two of the subject areas listed below * An author of an accepted paper must attend the symposium in person to give a presentation * Accepted full papers will be published as peer-reviewed online proceedings on arXiv.

Submission Format

  • Maximum of 6 pages, excluding references.
  • Submissions must be anonymized for double-blind review.
  • For paper formatting, please use the tinyML Research Symposium Template.

Subject Areas related to tinyML and Edge AI

  • Datasets and Data Collection: Public release of new datasets to tinyML; frameworks that automate dataset development; survey and analysis of existing tiny datasets that can be used for research, labeling, self-reports and annotation techniques; multimodal sensing.
  • Applications: Novel applications across all fields and emerging use cases; discussions about real-world use cases and deployments; user behavior and system-user interaction; survey on practical experiences.
  • AI Algorithms: Efficient AI and optimisation techniques including pruning, quantization, optimization methods; compressive sensing, continual and on-device learning; stream-based active learning methods; emerging algorithms for low-footprint computing; Generative AI ; security and privacy implications.
  • Systems: Profiling tools for measuring and characterizing performance and power; design space exploration frameworks; solutions that involve hardware and software co-design; characterization of tiny real-world embedded systems; concurrency and parallel processing, distributed and federated Learning, in- and near-sensor processing, design, and implementation; heterogeneous computing platforms.
  • Software: Interpreters and code generator frameworks for tiny systems; compilers and optimizations for efficient execution; MLOps; integrated environments for end-to-end development; software memory optimizations; neural architecture search methods.
  • Hardware: MCU, neural accelerators, architecture design and evaluation; circuit and architecture design for digital, analog and in- or near-memory processing; ultra-low-power memory system design; analogue computing, brain-inspired/neuromorphic computing; emerging hardware architectures for the extreme edge; power management.
  • Performance Evaluation and testing: Measurement tools and techniques; benchmark creation, assessment and validation; evaluation and measurement of real production systems, reliability, security , user testing in real-world settings.

Technical Program Committee

Amey Kulkarni, Nvidia
Ankita Nayak, Qualcomm
Arman Roohi, UIC
Avik Santra, Infinenon
Brian Plancher, Columbia University
Kiruba Subramani, Silabs
Manuel Roveri, Politecnico di Milano
Marcelo Rovai, Federal University of Itajuba - UNIFEI
Marco Zennaro, ICTP
Nitin CHAWLA, STMicroelectronics
Peters Christian, Bosch
Qianyun Lu, NXP
Bhardwaj Kshitij, LLNL.GOV
Alessio Burrello, Politecnico di Torino
Guilherme Paim, IEEE
Tobias Gemmeke, RWTH Aachen University
Laura Galindez, Archetype AI
Hana Khamfroush, UKY.EDU
Peter Chang, Skymizer
Petruț Antoniu Bogdan Innatera
Abbas Rahimi IBM
Aydin Aysu North Carolina State University
Angizi Shaahin New Jersey Institute of Technology
Sebastián Romero University of Puerto Rico at Mayagüez

See HotCRP submission portal.