Call for Papers

We invite researchers to submit papers related to on-device machine learning or any of the broad workshop themes in the following areas:

Areas/Topics

On-device ML Algorithms for efficient training/inference & privacy, including but not limited to

  • Learning efficient ML models under compute/memory/power constraints
  • Model compression for deep networks and other ML models
  • Privacy preserving machine learning
  • Low-precision training/inference


On-Device ML Frameworks & Hardware, including but not limited to

  • Mobile-optimized neural network libraries (e.g., CoreML, Caffe2 for mobile, TensorFlow Lite)
  • Hardware acceleration for neural computing on mobile devices
  • Open-source software packages to build and deploy on-device models
  • Developer tools/packages


Applications of On-Device ML, including but not limited to

  • Real-time mobile computer vision
  • Language understanding and conversational assistants on mobile and wearable devices
  • Speech recognition on mobile and smart home devices
  • ML for Robotics
  • Machine intelligence for mobile gaming
  • ML for mobile health and related real-time prediction scenarios
  • ML for on-device applications in the automotive industry (e.g., computer vision for self-driving cars)


We invite three types of submissions:

  • Research papers
  • Posters presentations
  • Demos

Submission Instructions

Authors should submit anonymous extended abstracts of 2 to 4 pages and additional references in PDF format using the NIPS style. If the work appeared in a previous research venue (journal, workshop, or conference including NIPS 2018 conference), the workshop submission should extend that previous work.

This year submissions will be accepted as contributed talks, poster presentations or demos. Please specify submission type, if there is a preference (note: the final determination will be made by the committee after review).

Send (email) your submissions here: nips2018-on-device-ml@googlegroups.com

Key Dates

  • Submission Deadline: Oct 26, 2018
  • Notification: Nov 5, 2018
  • Workshop: December 7, 2018