Cover Image

On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Lianming, Hu, Haibo, Li, Qiao, Guan, Nan, Xue, Chun Jason
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
by: HU, Haibo, et al.
Published: (2025)

AD-EE: Early Exiting for Fast and Reliable Vision-Language Models in Autonomous Driving
by: Huang, Lianming, et al.
Published: (2025)

GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
by: Huang, Lianming, et al.
Published: (2025)

Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling
by: Zhou, Zikang, et al.
Published: (2026)

RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning
by: Zuo, Jiacheng, et al.
Published: (2025)

Timely Fusion of Surround Radar/Lidar for Object Detection in Autonomous Driving Systems
by: Xie, Wenjing, et al.
Published: (2023)

Efficient Driving Behavior Narration and Reasoning on Edge Device Using Large Language Models
by: Huang, Yizhou, et al.
Published: (2024)

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
by: Li, Shanshan, et al.
Published: (2025)

EdgeEar: Efficient and Accurate Ear Recognition for Edge Devices
by: Lendering, Camile, et al.
Published: (2025)

Efficient Multi-Object Tracking on Edge Devices via Reconstruction-Based Channel Pruning
by: Müller, Jan, et al.
Published: (2024)

NuWa: Deriving Lightweight Task-Specific Vision Transformers for Edge Devices
by: Wei, Ziteng, et al.
Published: (2025)

Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference
by: Liu, Xiang, et al.
Published: (2024)

LWMSCNN-SE: A Lightweight Multi-Scale Network for Efficient Maize Disease Classification on Edge Devices
by: Weloday, Fikadu, et al.
Published: (2026)

Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection
by: Asare, Akwasi, et al.
Published: (2025)

Towards Efficient Image Deblurring for Edge Deployment
by: Miriyala, Srinivas, et al.
Published: (2026)

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
by: Wang, Zhibo, et al.
Published: (2026)

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
by: Kodavanti, Sravanth, et al.
Published: (2026)

Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis
by: Szankin, Maciej, et al.
Published: (2025)

CFIS-YOLO: A Lightweight Multi-Scale Fusion Network for Edge-Deployable Wood Defect Detection
by: Kang, Jincheng, et al.
Published: (2025)

Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment
by: Wu, Jiaqi, et al.
Published: (2024)

Extreme Model Compression with Structured Sparsity at Low Precision
by: Liu, Dan, et al.
Published: (2025)

Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
by: Hu, Haibo, et al.
Published: (2025)

Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices
by: Pan, Baiyu, et al.
Published: (2024)

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
by: Shao, Wenqi, et al.
Published: (2023)

EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning
by: Donga, Runchu, et al.
Published: (2025)

NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning
by: Mu, Tianwei, et al.
Published: (2025)

Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
by: Baker, Nermeen Abou, et al.
Published: (2026)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
by: Liu, Xuewen, et al.
Published: (2025)

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
by: Guan, Jiwei, et al.
Published: (2026)

Understanding and Harnessing Sparsity in Unified Multimodal Models
by: He, Shwai, et al.
Published: (2025)

Few-Shot Deployment of Pretrained MRI Transformers in Brain Imaging Tasks
by: Li, Mengyu, et al.
Published: (2025)

Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
by: Choi, Hyun-Ho, et al.
Published: (2025)

Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models
by: Liu, Xiao, et al.
Published: (2024)

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
by: Fan, Yingqi, et al.
Published: (2026)

Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks
by: Park, Yeji, et al.
Published: (2025)

Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks
by: Wang, Zhenyu, et al.
Published: (2024)

EdgeNAT: Transformer for Efficient Edge Detection
by: Jie, Jinghuai, et al.
Published: (2024)

Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment
by: Lu, Haisheng, et al.
Published: (2024)

Large Language Model with Region-guided Referring and Grounding for CT Report Generation
by: Chen, Zhixuan, et al.
Published: (2024)

Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement
by: To-Thanh, Dat, et al.
Published: (2026)