# Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables

arXiv: https://arxiv.org/abs/2401.08637 · HTML: https://mlsanity.com/paper/2401.08637/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 73 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing](https://mlsanity.com/paper/1611.01942/) (2016)
- [CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices](https://mlsanity.com/paper/2012.03257/) (2020)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers](https://mlsanity.com/paper/1905.12107/) (2019)
- [Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers](https://mlsanity.com/paper/1905.13082/) (2019)
- [Auto-Split: A General Framework of Collaborative Edge-Cloud AI](https://mlsanity.com/paper/2108.13041/) (2021)
- [Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures](https://mlsanity.com/paper/1608.06037/) (2016)
- [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://mlsanity.com/paper/2306.00001/) (2023)
- [Differentiable Network Pruning for Microcontrollers](https://mlsanity.com/paper/2110.08350/) (2021)
- [The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox](https://mlsanity.com/paper/1409.3809/) (2014)
- [DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices](https://mlsanity.com/paper/2202.01699/) (2022)
- [WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes](https://mlsanity.com/paper/2002.04597/) (2020)
- [AdaMEC: Towards a Context-Adaptive and Dynamically-Combinable DNN Deployment Framework for Mobile Edge Computing](https://mlsanity.com/paper/2310.16547/) (2023)

## Built on by (most cited first, 1 of 1)

- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)

## Abstract (arXiv)

The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrated into wearable devices, these accelerators open exciting opportunities, allowing various AI apps to run directly on the body. We present Synergy that provides AI apps with best-effort performance via system-driven holistic collaboration over AI accelerator-equipped wearables. To achieve this, Synergy provides device-agnostic programming interfaces to AI apps, giving the system visibility and controllability over the app's resource use. Then, Synergy maximizes the inference throughput of concurrent AI models by creating various execution plans for each app considering AI accelerator availability and intelligently selecting the best set of execution plans. Synergy further improves throughput by leveraging parallelization opportunities over multiple computation units. Our evaluations with 7 baselines and 8 models demonstrate that, on average, Synergy achieves a 23.0 times improvement in throughput, while reducing latency by 73.9% and power consumption by 15.8%, compared to the baselines.