Neiwen Ling

Selected Publications

1. SenSys’22

   BlastNet: Exploiting Duo-Blocks for Cross-Processor Real-Time DNN Inference

   Neiwen Ling, Xuan Huang, Zhihe Zhao, Nan Guan, Zhenyu Yan, and Guoliang Xing

   The 20th ACM Conference on Embedded Networked Sensor Systems (ACM SenSys 2022)
   Best Paper Finalist

   Abs HTML PDF Slides

   In recent years, Deep Neural Network (DNN) has been increasingly adopted by a wide range of time-critical applications running on edge platforms with heterogeneous multiprocessors. To meet the stringent timing requirements of these applications, heterogeneous CPU and GPU resources must be efficiently utilized for the inference of multiple DNN models. Such a cross-processor real-time DNN inference paradigm poses major challenges due to the inherent performance imbalance among different processors and the lack of real-time support for cross-processor inference from existing deep learning frameworks. In this work, we propose a new system named BlastNet that exploits duo-block - a new model inference abstraction to support highly efficient cross-processor real-time DNN inference. Each duo-block has a dual model structure, enabling efficient fine-grained inference alternatively across different processors. BlastNet employs a novel block-level Neural Architecture Search (NAS) technique to generate duo-blocks, which accounts for computing characteristics and communication overhead. The duoblocks are optimized at design time and then dynamically scheduled to achieve high resource utilization of heterogeneous CPU and GPU at runtime. BlastNet is implemented on an indoor autonomous driving platform and three popular edge platforms. Extensive results show that BlastNet achieves 35.07 % less deadline missing rate with a mere 1.63% of model accuracy loss.

2. MobiSys’26

   TimelyLLM: Time-sensitive LLM Serving System for Physical-I/O Limited Agents

   Neiwen Ling, Guojun Chen, Anurag Khandelwal, and Lin Zhong

   Conditionally accepted by The 23rd ACM International Conference on Mobile Systems, Applications, and Services (ACM MobiSys 2026)

   Abs HTML PDF

   Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing LLM serving systems typically employ a first-come, first-served (FCFS) batching mechanism, which fails to address the time-sensitive requirements of robotic applications. To address it, this paper proposes a new system named TimelyLLM serving multiple robotic agents with time-sensitive requests. TimelyLLM introduces novel mechanisms of segmented generation and scheduling that optimally leverage redundancy between robot plan generation and execution phases. We report an implementation of TimelyLLM on a widely-used LLM serving framework and evaluate it on a range of robotic applications. Our evaluation shows that TimelyLLM improves the time utility up to 1.97x, and reduces the overall waiting time by 84%.

3. SenSys’21

   RT-mDL: Supporting Real-Time Mixed Deep Learning Tasks on Edge Platforms

   Neiwen Ling, Kai Wang, Yuze He, Guoliang Xing, and Daqi Xie

   The 19th ACM Conference on Embedded Networked Sensor Systems (ACM SenSys 2021)

   Abs HTML Video Demo PDF Slides

   Recent years have witnessed an emerging class of real-time applications, e.g., autonomous driving, in which resource-constrained edge platforms need to execute a set of real-time mixed Deep Learning (DL) tasks concurrently. Such an application paradigm poses major challenges due to the huge compute workload of deep neural network models, diverse performance requirements of different tasks, and the lack of real-time support from existing DL frameworks. In this paper, we present RT-mDL, a novel framework to support mixed real-time DL tasks on edge platform with heterogeneous CPU and GPU resource. RT-mDL aims to optimize the mixed DL task execution to meet their diverse real-time/accuracy requirements by exploiting unique compute characteristics of DL tasks. RT-mDL employs a novel storage-bounded model scaling method to generate a series of model variants, and systematically optimizes the DL task execution by joint model variants selection and task priority assignment. To improve the CPU/GPU utilization of mixed DL tasks, RT-mDL also includes a new priority-based scheduler which employs a GPU packing mechanism and executes the CPU/GPU tasks independently. Our implementation on an F1/10 autonomous driving testbed shows that, RT-mDL can enable multiple concurrent DL tasks to achieve satisfactory real-time performance in traffic light detection and sign recognition. Moreover, compared to state-of-the-art baselines, RT-mDL can reduce deadline missing rate by 40.12% while only sacrificing 1.7% model accuracy.

4. MobiCom’24

   Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving

   Shuyao Shi(co-primary), Neiwen Ling(co-primary), Zhehao Jiang(co-primary), Xuan Huang(co-primary), Yuze He, Xiaoguang Zhao, Bufang Yang, Chen Bian, and 4 more authors

   The 30th Annual International Conference on Mobile Computing And Networking (ACM MobiCom 2024)
   Best Artifact Award Runner-Up

   Abs HTML PDF

   Recently, smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted autonomous driving, this paper presents the design and deployment of Soar, the first end-to-end SRI system specifically designed to support autonomous driving systems. Soar consists of both software and hardware components carefully designed to overcome various system and physical challenges. Soar can leverage the existing operational infrastructure like street lampposts for a lower barrier of adoption. Soar adopts a new communication architecture that comprises a bi-directional multi-hop I2I network and a downlink I2V broadcast service, which are designed based on off-the-shelf 802.11ac interfaces in an integrated manner. Soar also features a hierarchical DL task management framework to achieve desirable load balancing among nodes and enable them to collaborate efficiently to run multiple data-intensive autonomous driving applications. We deployed a total of 18 Soar nodes on existing lampposts on campus, which have been operational for over two years. Our real-world evaluation shows that Soar can support a diverse set of autonomous driving applications and achieve desirable real-time performance and high communication reliability. Our findings and experiences in this work offer key insights into the development and deployment of next-generation smart roadside infrastructure and autonomous driving systems.

5. TMC’25

   Time-sensitive Multi-DNN Inference on CPU-GPU Edge Platforms

   Neiwen Ling, Wenrui Lu, Xuan Huang, Zhihe Zhao, Nan Guan, Zhenyu Yan, and Guoliang Xing

   IEEE Transactions on Mobile Computing (IEEE TMC 2025)
6. IPSN’23

   CoEdge: A Cooperative Edge System for Distributed Real-Time Deep Learning Tasks

   Zhehao Jiang(co-primary), Neiwen Ling(co-primary), Xuan Huang, Shuyao Shi, Chenhao Wu, Xiaoguang Zhao, Zhenyu Yan, and Guoliang Xing

   The 22nd ACM/IEEE Conference on Information Processing in Sensor Networks (ACM/IEEE IPSN 2023)

   Abs HTML PDF Slides

   Recent years have witnessed the emergence of a new class of cooperative edge systems in which a large number of edge nodes can collaborate through local peer-to-peer connectivity. In this paper, we propose CoEdge, a novel cooperative edge system that can support concurrent data/compute-intensive deep learning (DL) models for distributed real-time applications such as city-scale traffic monitoring and autonomous driving. First, CoEdge includes a hierarchical DL task scheduling framework that dispatches DL tasks to edge nodes based on their computational profiles, communication overhead, and real-time requirements. Second, CoEdge can dramatically increase the execution efficiency of DL models by batching sensor data and aggregating the inferences of the same model. Finally, we propose a new edge containerization approach that enables an edge node to execute concurrent DL tasks by partitioning the CPU and GPU workloads into different containers. We extensively evaluate CoEdge on a self-deployed smart lamppost testbed on a university campus. Our results show that CoEdge can achieve up to 82.32% reduction on deadline missing rate compared to baselines.

7. TMC’25

   TypeFly: Low-Latency Drone Planning with Large Language Models

   Guojun Chen, Xiaojing Yu, Neiwen Ling, and Lin Zhong

   IEEE Transactions on Mobile Computing (IEEE TMC 2025)

   Abs

8. SenSys’22Poster

   Aaron: Compile-time Kernel Adaptation for Multi-DNN Inference Acceleration on Edge GPU

   Zhihe Zhao, Neiwen Ling, Nan Guan, and Guoliang Xing

   The 20th ACM Conference on Embedded Networked Sensor Systems
   Best Poster Award

   Abs HTML PDF

   AI applications powered by deep learning are increasingly running on edge devices. Meanwhile, many real-world IoT applications demand multiple real-time tasks to run on the same device, for example, to achieve both object tracking and image segmentation simultaneously on an augmented reality glass. However, the current solutions can not yet support such multi-tenant real-time DNN inference on edge devices. Techniques such as on-device model compression trade inference accuracy for speed, while traditional DNN compilers mainly focus on single-tenant DNN model optimization. To fill this gap, we propose Aaron, which leverages DNN compiling techniques to accelerate multi-DNN inference on edge GPU based on compile-time kernel adaptation with no accuracy loss. Aaron integrates both DNN graph and kernel optimization to maximize on-device parallelism and minimize contention brought by concurrent inference.

9. SenSys’23

   Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU

   Zhihe Zhao, Neiwen Ling, Nan Guan, and Guoliang Xing

   The 21st ACM Conference on Embedded Networked Sensor Systems (ACM SenSys 2023)

   Abs HTML PDF

   Many applications such as autonomous driving and augmented reality, require the concurrent running of multiple deep neural networks (DNN) that poses different levels of real-time performance requirements. However, coordinating multiple DNN tasks wth varying levels of criticality on edge GPUs remains an area of limited study. Unlike server-level GPUs, edge GPUs are resourcelimited and lack hardware-level resource management mechanisms for avoiding resource contention. Therefore, we propose Miriam, a contention-aware task coordination framework for multi-DNN inference on edge GPU. Miriam consolidates two main components, an elastic-kernel generator, and a runtime dynamic kernel coordinator, to support mixed critical DNN inference. To evaluate Miriam, we build a new DNN inference benchmark based on CUDA with diverse representative DNN workloads. Experiments on two edge GPU platforms show that Miriam can increase system throughput by 92% while only incurring less than 10% latency overhead for critical tasks, compared to state of art baselines.

10. SenSys’23

    EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge

    Bufang Yang, Lixing He, Neiwen Ling, Zhenyu Yan, Guoliang Xing, Xian Shuai, Ren Xiaozhe, and Xin Jiang

    The 21st ACM Conference on Embedded Networked Sensor Systems (ACM SenSys 2023)

    Abs PDF

    Deep Learning (DL) models have been widely deployed on IoT devices with the help of advancements in DL algorithms and chips. However, the limited resources of edge devices make these ondevice DL models hard to be generalizable to diverse environments and tasks. Although the recently emerged foundation models (FMs) show impressive generalization power, how to effectively leverage the rich knowledge of FMs on resource-limited edge devices is still not explored. In this paper, we propose EdgeFM, a novel edge-cloud cooperative system with open-set recognition capability. EdgeFM selectively uploads unlabeled data to query the FM on the cloud and customizes the specific knowledge and architectures for edge models. Meanwhile, EdgeFM conducts dynamic model switching at run-time taking into account both data uncertainty and dynamic network variations, which ensures the accuracy always close to the original FM. We implement EdgeFM using two FMs on two edge platforms. We evaluate EdgeFM on three public datasets and two self-collected datasets. Results show that EdgeFM can reduce the end-to-end latency up to 3.2x and achieve 34.3% accuracy increase compared with the baseline.