Mobile Agentic Systems

Overview

AI technologies have increasingly penetrated applications running on mobile/edge devices, e.g., mobile phones and smart cameras. Yet, deploying state-of-the-art AI models with billions of parameters on resource-constrained mobile/edge devices still faces critical challenges due to the stringent compute and memory requirements of running these models. We are investigating solutions to address this timely problem, mainly in two directions: (1) optimizing the computations of large AI models to fit them to the resources of mobile/edge devices by leveraging sparsity and locality, and (2) offloading intensive AI inference workloads to an edge or cloud platform where more computational resources are available, while handling the inherent network variability.

People

Publications

  • DATE 2027
    Optimizing LLM Inference on Heterogeneous Edge SoCs with Operator-Level Controls
    Hanzhang Ma, Qianjun Zheng, Bohua Zou, Debayan Roy, Sudeep Kanav, Binqi Sun, Lin Wang, Yutao Liu
    IEEE Design, Automation, and Test in Europe (DATE), 2027
  • arXiv 2026
    SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
    Huzaifa Shaaban Kabakibo, Eric Schniedermeyer, Artem Burchanow, Lin Wang
    arXiv, 2026
  • MobiCom 2025
    Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices
    Guilherme Henrique Apostolo, Pablo Bauszat, Vinod Nigade, Henri E. Bal, Lin Wang
    ACM Annual International Conference on Mobile Computing and Networking (MobiCom), 2025
  • TPDS 2024
    Graft: Efficient Inference Serving for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment
    Jing Wu, Lin Wang, Qirui Jin, Fangming Liu
    IEEE Transactions on Parallel and Distributed Systems (TPDS), 2024
  • EuroMLSys 2022
    Live Video Analytics as a Service
    Guilherme H. Apostolo, Pablo Bauszat, Vinod Nigade, Henri E. Bal, Lin Wang
    ACM European Workshop on Machine Learning and Systems (EuroMLSys), 2022
  • RTSS 2022Outstanding Paper Award
    Jellyfish: Timely Inference Serving for Dynamic Edge Networks
    Vinod Nigade, Pablo Bauszat, Henri E. Bal, Lin Wang
    IEEE Real-Time Systems Symposium (RTSS), 2022
  • TPDS 2022
    HiTDL: High-Throughput Deep Learning Inference at the Hybrid Mobile Edge
    Jing Wu, Lin Wang, Qiangyu Pei, Xingqi Cui, Fangming Liu, Tingting Yang
    IEEE Transactions on Parallel and Distributed Systems (TPDS), 2022
  • SEC 2020
    Clownfish: Edge and Cloud Symbiosis for Video Stream Analytics
    Vinod Nigade, Lin Wang, Henri E. Bal
    IEEE/ACM Symposium on Edge Computing (SEC), 2020