Image de couverture de livre

$D^2Prune$: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xiong, Lang, Liu, Ning, Ren, Ao, Bai, Yuheng, Fang, Haining, Zhang, BinYan, Jiang, Zhe, Tan, Yujuan, Liu, Duo
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Trustworthy Self-Attention: Enabling the Network to Focus Only on the Most Relevant References
par: Jing, Yu, et autres
Publié: (2024)

YOIO: You Only Iterate Once by mining and fusing multiple necessary global information in the optical flow estimation
par: Jing, Yu, et autres
Publié: (2024)

FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
par: Li, Li, et autres
Publié: (2021)

CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
par: Zhang, Yu, et autres
Publié: (2021)

Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
par: Duan, Moming, et autres
Publié: (2021)

Analysis of the Riemann Zeta Function via Recursive Taylor Expansions
par: Bai, Yunwei
Publié: (2026)

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
par: Wang, Guanchu, et autres
Publié: (2024)

Bishop: Sparsified Bundling Spiking Transformers on Heterogeneous Cores with Error-Constrained Pruning
par: Xu, Boxun, et autres
Publié: (2025)

Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding
par: Berestizshevsky, Konstantin, et autres
Publié: (2025)

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
par: Sun, Ao, et autres
Publié: (2026)

Extensional Taylor Expansion
par: Blondeau-Patissier, Lison, et autres
Publié: (2023)

Lower Bounds on Flow Sparsifiers with Steiner Nodes
par: Chen, Yu, et autres
Publié: (2026)

FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation
par: Zhu, Shaolin, et autres
Publié: (2025)

FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measure
par: Duan, Moming, et autres
Publié: (2020)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
par: Liu, Zheyuan, et autres
Publié: (2025)

Unfolding Videos Dynamics via Taylor Expansion
par: Chen, Siyi, et autres
Publié: (2024)

Sparsifying Sums of Positive Semidefinite Matrices
par: Basu, Arpon, et autres
Publié: (2025)

High-Layer Attention Pruning with Rescaling
par: Liu, Songtao, et autres
Publié: (2025)

Assessing Gender and Racial Bias in Large Language Model‐Powered Virtual Reference
par: Jieli Liu, et autres
Publié: (2024)

Cut-Preserving Vertex Sparsifiers for Planar and Quasi-bipartite Graphs
par: Chen, Yu, et autres
Publié: (2024)

Learning to Sparsify Stochastic Linear Bandits
par: Wang, Zhengmiao, et autres
Publié: (2026)

Taylor Expansion of homogeneous functions
par: Paulusch, Joachim, et autres
Publié: (2021)

Distribution-Aware Data Expansion with Diffusion Models
par: Zhu, Haowei, et autres
Publié: (2024)

Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
par: Li, Qingbiao, et autres
Publié: (2020)

SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
par: Jiao, Difan, et autres
Publié: (2023)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
par: Liu, Jizhihui, et autres
Publié: (2025)

Cross-Attention Graph Neural Networks for Inferring Gene Regulatory Networks with Skewed Degree Distribution
par: Xiong, Jiaqi, et autres
Publié: (2024)

V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
par: Lin, Xinying, et autres
Publié: (2026)

Image Super-Resolution with Taylor Expansion Approximation and Large Field Reception
par: Feng, Jiancong, et autres
Publié: (2024)

Near-Optimal Sparsifiers for Stochastic Knapsack and Assignment Problems
par: Dughmi, Shaddin, et autres
Publié: (2025)

Twice-Ramanujan Sparsifiers
par: Batson, Joshua, et autres
Publié: (2008)

Many Hamiltonians Are Sparsifiable
par: Basu, Arpon, et autres
Publié: (2026)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
par: Wang, Xinhao, et autres
Publié: (2026)

Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization
par: Liu, Duo, et autres
Publié: (2025)

PAT: Pruning-Aware Tuning for Large Language Models
par: Liu, Yijiang, et autres
Publié: (2024)

FedSRD: Sparsify-Reconstruct-Decompose for Communication-Efficient Federated Large Language Models Fine-Tuning
par: Yan, Guochen, et autres
Publié: (2025)

Dispatch-Aware Ragged Attention for Pruned Vision Transformers
par: Abdellatif, Seifeldin, et autres
Publié: (2026)

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models
par: Wei, Qianshan, et autres
Publié: (2025)

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning
par: Guo, Yiju, et autres
Publié: (2025)

Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning
par: Xu, Lizhen, et autres
Publié: (2025)