paper-with-me

홈 › Papers

MMEdge: Accelerating On-device Multimodal Inference via Pipelined Sensing and Encoding

2025-10-29 · Runxi Huang, Mingxuan Yu, Mingyu Tsoi, Xiaomin Ouyang arxiv

Real-time multimodal inference on resource-constrained edge devices is essential for applications such as autonomous driving, human-computer interaction, and mobile health. However, prior work often overlooks the tight coupling between sensing dynamics and model execution, as well as the complex inter-modality dependencies. In this paper, we propose MMEdge, a new on-device multimodal inference framework based on pipelined sensing and encoding. Instead of waiting for complete sensor inputs, MMEdge decomposes the entire inference process into a sequence of fine-grained sensing and encoding units, allowing computation to proceed incrementally as data arrive. MMEdge also introduces a lightweight but effective temporal aggregation module that captures rich temporal dynamics across different pipelined units to maintain accuracy performance. Such pipelined design also opens up opportunities for fine-grained cross-modal optimization and early decision-making during inference. To further enhance system performance under resource variability and input data complexity, MMEdge incorporates an adaptive multimodal configuration optimizer that dynamically selects optimal sensing and model configurations for each modality under latency constraints, and a cross-modal speculative skipping mechanism that bypasses future units of slower modalities when early predictions reach sufficient confidence. We evaluate MMEdge using two public multimodal datasets and deploy it on a real-world unmanned aerial vehicle (UAV)-based multimodal testbed. The results show that MMEdge significantly reduces end-to-end latency while maintaining high task accuracy across various system and data dynamics. A video demonstration of MMEdge's performance in real world is available at https://youtu.be/qRew7sT-iWw.

📄 PDF Abstract BibTeX arXiv:2510.25327

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference

2026-04-30 · Ali Emre Oztas, Mahir Demir, James Garside, Mikel Luján arxiv

Video and image streaming on edge devices requires low latency. To address this, Neural Networks (NNs) are widely used, and prior work mainly focuses on accelerating them with single hardware units such as Graphics Proce…

Graph Neural Network

Hardware-efficient on-line learning through pipelined truncated-error backpropagation in binary-state networks

2017-06-15 · Hesham Mostafa, Bruno Pedroni, Sadique Sheik, Gert Cauwenberghs

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing…

PIPO: Pipelined Offloading for Efficient Inference on Consumer Devices

2025-03-15 · Yangyijian Liu, Jun Li, Wu-Jun Li

The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers …

GPUScheduling

SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices

2023-09-04 · Alexander Montgomerie-Corcoran, Petros Toupas, Zhewen Yu, Christos-Savvas Bouganis

AI has led to significant advancements in computer vision and image processing tasks, enabling a wide range of applications in real-life scenarios, from autonomous vehicles to medical imaging. Many of those applications …

Autonomous VehiclesGPUObjectobject-detection+1

A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization

2021-10-10 · Yuyang Zhang, Dik Hin Leung, Min Guo, Yijia Xiao 외

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve…

Edge-computingQ-LearningQuantization