Imagen de Portada

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Zihuai, Xu, Yang, Xu, Hongli, Liao, Yunming, Yao, Zhiwei, Xie, Zuan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient Deployment of Large Language Models on Resource-constrained Devices
por: Yao, Zhiwei, et al.
Publicado: (2025)

A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language Models
por: Xie, Zuan, et al.
Publicado: (2025)

Resource-Efficient Federated Fine-Tuning Large Language Models for Heterogeneous Data
por: Liu, Jun, et al.
Publicado: (2025)

Collaborative Inference for Large Models with Task Offloading and Early Exiting
por: Xie, Zuan, et al.
Publicado: (2024)

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
por: Song, Siqing, et al.
Publicado: (2026)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
por: Lu, Yao, et al.
Publicado: (2025)

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
por: Xiao, He, et al.
Publicado: (2025)

Post Training Quantization of Large Language Models with Microscaling Formats
por: Sharify, Sayeh, et al.
Publicado: (2024)

Achieving binary weight and activation for LLMs using Post-Training Quantization
por: Song, Siqing, et al.
Publicado: (2025)

Understanding Post-Training Structural Changes in Large Language Models
por: He, Xinyu, et al.
Publicado: (2025)

Activation Sensitivity as a Unifying Principle for Post-Training Quantization
por: Xu, Bruce Changlong
Publicado: (2026)

Training Large Language Models to Reason via EM Policy Gradient
por: Xu, Tianbing
Publicado: (2025)

BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs
por: Zhao, Zhixiong, et al.
Publicado: (2026)

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

PT$^2$-LLM: Post-Training Ternarization for Large Language Models
por: Yan, Xianglong, et al.
Publicado: (2025)

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
por: Xiao, He, et al.
Publicado: (2025)

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation
por: Liao, Yunming, et al.
Publicado: (2023)

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
por: Cho, Yeseul, et al.
Publicado: (2025)

A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models
por: Lu, Yao, et al.
Publicado: (2024)

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services
por: Zhao, Fei, et al.
Publicado: (2025)

SwiftPrune: Hessian-Free Weight Pruning for Large Language Models
por: Kang, Yuhan, et al.
Publicado: (2025)

Text Quality-Based Pruning for Efficient Training of Language Models
por: Sharma, Vasu, et al.
Publicado: (2024)

Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
por: Yang, Hao, et al.
Publicado: (2025)

Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices
por: Liu, Jun, et al.
Publicado: (2024)

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
por: Zhao, Zhixiong, et al.
Publicado: (2026)

Large Language Model Unlearning
por: Yao, Yuanshun, et al.
Publicado: (2023)

Lightweight Edge Learning via Dataset Pruning
por: Ale, Laha, et al.
Publicado: (2026)

BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
por: Zou, Bo, et al.
Publicado: (2026)

Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving
por: Su, Wensheng, et al.
Publicado: (2024)

P$^2$ Law: Scaling Law for Post-Training After Model Pruning
por: Chen, Xiaodong, et al.
Publicado: (2024)

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
por: Liu, Xiaoyun, et al.
Publicado: (2026)

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
por: Zhao, Shiwan, et al.
Publicado: (2026)

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
por: Xie, Yanyue, et al.
Publicado: (2024)

Lightweight Safety Classification Using Pruned Language Models
por: Sawtell, Mason, et al.
Publicado: (2024)

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
por: Zhang, Kaichen, et al.
Publicado: (2025)

FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition
por: Lu, Yao, et al.
Publicado: (2025)

DiRL: An Efficient Post-Training Framework for Diffusion Language Models
por: Zhu, Ying, et al.
Publicado: (2025)

LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
por: Qiao, Yiran, et al.
Publicado: (2024)

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
por: Xu, Yuanda, et al.
Publicado: (2026)

Symmetric Pruning of Large Language Models
por: Yi, Kai, et al.
Publicado: (2025)