paper-with-me

Papers

Accelerating Mobile Edge Generation (MEG) by Constrained Learning

2024-07-09 · Xiaoxia Xu, Yuanwei Liu, Xidong Mu, Hong Xing, Arumugam Nallanathan

A novel accelerated mobile edge generation (MEG) framework is proposed for generating high-resolution images on mobile devices. Exploiting a large-scale latent diffusion model (LDM) distributed across edge server (ES) and user equipment (UE), cost-efficient artificial intelligence generated content (AIGC) is achieved by transmitting low-dimensional features between ES and UE. To reduce overheads of both distributed computations and transmissions, a dynamic diffusion and feature merging scheme is conceived. By jointly optimizing the denoising steps and feature merging ratio, the image generation quality is maximized subject to latency and energy consumption constraints. To address this problem and tailor LDM sub-models, a low-complexity MEG acceleration protocol is developed. Particularly, a backbone meta-architecture is trained via offline distillation. Then, dynamic diffusion and feature merging are determined in online channel environment, which can be viewed as a constrained Markov Decision Process (MDP). A constrained variational policy optimization (CVPO) based MEG algorithm is further proposed for constraint-guaranteed learning, namely MEG-CVPO. Numerical results verify that: 1) The proposed framework can generate 1024$\times$1024 high-quality images over noisy channels while reducing over $40\%$ latency compared to conventional generation schemes. 2) The developed MEG-CVPO effectively mitigates constraint violations, thus flexibly controlling the trade-off between image distortion and generation costs.

📄 PDF Abstract BibTeX arXiv:2407.07245

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage Generation

Methods 이 논문이 사용한 방법론

Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Resource-efficient Generative Mobile Edge Networks in 6G Era: Fundamentals, Framework and Case Study

2023-12-19 · Bingkun Lai, Jinbo Wen, Jiawen Kang, Hongyang Du 외

As the next-generation wireless communication system, Sixth-Generation (6G) technologies are emerging, enabling various mobile edge networks that can revolutionize wireless communication and connectivity. By integrating …

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

2021-05-17 · Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes 외

Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even fo…

Image Super-ResolutionSuper-Resolution

RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices

2024-09-27 · Kam Chi Loong, Shihao Han, Sishuo Liu, Ning Lin 외

Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficiency compared to conventional von Neumann a…

Neural Architecture Search

Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

2026-03-12 · Xiaobiao Du, Yida Wang, Kun Zhan, Xin Yu arxiv

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications.However, its high computational demands and large storage costs pose significant challe…

lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models

2025-10-07 · Haoxin Wang, Xiaolong Tu, Hongyu Ke, Huirong Chai 외 arxiv

Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs local…