# MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU

arXiv: https://arxiv.org/abs/1706.00878 · HTML: https://mlsanity.com/paper/1706.00878/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2017.

## Built on by (most cited first, 5 of 5)

- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [Boosting DNN Cold Inference on Edge Devices](https://mlsanity.com/paper/2206.07446/) (2022)
- [Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps](https://mlsanity.com/paper/2510.13405/) (2025)
- [Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences](https://mlsanity.com/paper/2603.21508/) (2026)

## Abstract (arXiv)

In this paper, we explore optimizations to run Recurrent Neural Network (RNN) models locally on mobile devices. RNN models are widely used for Natural Language Processing, Machine Translation, and other tasks. However, existing mobile applications that use RNN models do so on the cloud. To address privacy and efficiency concerns, we show how RNN models can be run locally on mobile devices. Existing work on porting deep learning models to mobile devices focus on Convolution Neural Networks (CNNs) and cannot be applied directly to RNN models. In response, we present MobiRNN, a mobile-specific optimization framework that implements GPU offloading specifically for mobile GPUs. Evaluations using an RNN model for activity recognition shows that MobiRNN does significantly decrease the latency of running RNN models on phones.