Cover Image

CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Jingxuan, Bao, Weidong, Wang, Ji, Zhong, Zhengyi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Multi-Task Modeling through Automated Fusion of Trained Models
by: Zhou, Jingxuan, et al.
Published: (2025)

Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter
by: Zhong, Zhengyi, et al.
Published: (2025)

Multi-task Federated Learning with Encoder-Decoder Structure: Enabling Collaborative Learning Across Different Tasks
by: Zhou, Jingxuan, et al.
Published: (2025)

SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
by: Zhong, Zhengyi, et al.
Published: (2025)

Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge
by: Hu, Senkang, et al.
Published: (2025)

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
by: Yu, Xingtong, et al.
Published: (2023)

Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
by: Trong, Thua Huynh, et al.
Published: (2024)

Gains: Fine-grained Federated Domain Adaptation in Open Set
by: Zhong, Zhengyi, et al.
Published: (2025)

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models
by: Xu, Zihuai, et al.
Published: (2025)

MoTE: Mixture of Task-specific Experts for Pre-Trained ModelBased Class-incremental Learning
by: Li, Linjie, et al.
Published: (2025)

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
by: Jia, Yongzhe, et al.
Published: (2024)

Recommending Pre-Trained Models for IoT Devices
by: Patil, Parth V., et al.
Published: (2024)

LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device
by: Wang, Zeqing, et al.
Published: (2024)

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
by: Wang, Chen, et al.
Published: (2026)

On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
by: Huang, Lianming, et al.
Published: (2025)

A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
by: Wang, Chenhan, et al.
Published: (2026)

TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training
by: Cheng, Guanjie, et al.
Published: (2026)

TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
by: Haque, Mohd Ariful, et al.
Published: (2025)

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
by: Wang, Xiaolei, et al.
Published: (2024)

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
by: Yin, Lu, et al.
Published: (2023)

Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning
by: Wang, Yan, et al.
Published: (2025)

LLM-based Knowledge Pruning for Time Series Data Analytics on Edge-computing Devices
by: Jin, Ruibing, et al.
Published: (2024)

Compact Language Models via Pruning and Knowledge Distillation
by: Muralidharan, Saurav, et al.
Published: (2024)

A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices
by: Gong, Chen, et al.
Published: (2025)

Unsupervised Training of Neural Cellular Automata on Edge Devices
by: Kalkhof, John, et al.
Published: (2024)

QAdaPrune: Adaptive Parameter Pruning For Training Variational Quantum Circuits
by: Kulshrestha, Ankit, et al.
Published: (2024)

AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices
by: Liu, Mengyang, et al.
Published: (2025)

TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training
by: Wang, Yifan, et al.
Published: (2025)

Accelerated Training on Low-Power Edge Devices
by: Ahmed, Mohamed Aboelenien, et al.
Published: (2025)

Boosted Trees on a Diet: Compact Models for Resource-Constrained Devices
by: Herrmann, Nina, et al.
Published: (2025)

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
by: Zhou, Wenjie, et al.
Published: (2026)

On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence
by: Huang, Jian, et al.
Published: (2025)

QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
by: Herath, Charuka, et al.
Published: (2026)

Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices
by: Uddin, Mohammed Mudassir, et al.
Published: (2026)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
by: Yu, Peiqi, et al.
Published: (2026)

EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models
by: Xing, Xingrun, et al.
Published: (2025)

GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices
by: Tu, Xiaolong, et al.
Published: (2025)

Graph Pre-Training Models Are Strong Anomaly Detectors
by: Cheng, Jiashun, et al.
Published: (2024)

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models
by: Costello, Caia, et al.
Published: (2025)

Frustratingly Easy Task-aware Pruning for Large Language Models
by: Tian, Yuanhe, et al.
Published: (2025)