We invite participation in the 3rd on-device intelligence workshop. We solicit high-quality research papers that demonstrate new results which relate to on-device machine learning.Â
Topics of Interest for solicited papers and posters include:
Novel on-device capabilities for vision, speech, and time series processing
On-device distributed privacy-preserving learning
Efficient machine learning models for edge devices
Dynamic neural networks such as early termination and mixture-of-experts
Platform-aware model optimization
Efficient hardware accelerator design for AI workloads
Tools for architecture modeling, design space exploration, and algorithm mapping
Efficient model execution strategies on edge devices such as scheduling and tiling
Emerging technologies such as near-sensor, -memory, and -storage computing
New application domains that utilize on-device intelligence
ML operations and coordination tools
On-device security for ML or ML for security
Emerging ethical and privacy implications of on-device intelligence
Submission Deadline: February 24th, 2023 @ 11:59pm AoE
Acceptance Notification: March 31st, 2023
Submissions should be four pages long with an additional page for references. Formatting should follow the guidance for MLSys 2023.
Authors are encouraged to submit original research (including those already available as a preprint), initial findings, and insights from research-in-progress or position papers on the above topics. The program committee will select submissions based on a combination of novelty, insightful or thought-provoking observations, and relevance to the workshop. Reviews will be single-blind.
Submission link: cmt3.research.microsoft.com/ODIW2023
At least one author of an accepted paper must attend the workshop in person. Authors of accepted papers will give a 3-minute lightning talk, followed by a 45-minute poster session. Authors must submit slides and a pdf of the poster a week before the workshop.