Imagen de Portada

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Shwai, Li, Ang, Chen, Tianlong
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
por: Li, Yue, et al.
Publicado: (2025)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
por: Wu, Zhenkai, et al.
Publicado: (2025)

Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
por: Ge, Shiran, et al.
Publicado: (2025)

CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
por: Aggarwal, Shivam, et al.
Publicado: (2023)

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
por: Meng, Xiang, et al.
Publicado: (2024)

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
por: Liu, Shiwei, et al.
Publicado: (2021)

Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
por: Zhang, Mingyuan, et al.
Publicado: (2025)

Data-independent Module-aware Pruning for Hierarchical Vision Transformers
por: He, Yang, et al.
Publicado: (2024)

CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
por: Jha, Samyak, et al.
Publicado: (2026)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
por: Li, Xue, et al.
Publicado: (2025)

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
por: Zhang, Yanan, et al.
Publicado: (2024)

Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
por: Li, Sijie, et al.
Publicado: (2026)

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
por: Zhang, Tianyu, et al.
Publicado: (2024)

Isomorphic Pruning for Vision Models
por: Fang, Gongfan, et al.
Publicado: (2024)

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
por: Farina, Matteo, et al.
Publicado: (2025)

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
por: Wang, Qinsi, et al.
Publicado: (2025)

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
por: Li, Chunxiao, et al.
Publicado: (2026)

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
por: Baek, Changwoo, et al.
Publicado: (2026)

LOTUS: Improving Transformer Efficiency with Sparsity Pruning and Data Lottery Tickets
por: Upadhyay, Ojasw
Publicado: (2024)

Training-Free Restoration of Pruned Neural Networks
por: Lee, Keonho, et al.
Publicado: (2025)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
por: Kim, Minsung, et al.
Publicado: (2025)

LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling
por: Li, Xin, et al.
Publicado: (2024)

MDP: Multidimensional Vision Model Pruning with Latency Constraint
por: Sun, Xinglong, et al.
Publicado: (2025)

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
por: Huang, Ning-Chi, et al.
Publicado: (2024)

Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning
por: Li, Andy, et al.
Publicado: (2024)

Investigating the Effect of Network Pruning on Performance and Interpretability
por: von Rad, Jonathan, et al.
Publicado: (2024)

Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
por: Özdenizci, Ozan, et al.
Publicado: (2022)

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers
por: Li, Andy, et al.
Publicado: (2026)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
por: Zhang, Dingkun, et al.
Publicado: (2026)

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
por: He, Chiyuan, et al.
Publicado: (2026)

Rethinking the Bias of Foundation Model under Long-tailed Distribution
por: Chen, Jiahao, et al.
Publicado: (2025)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
por: Jiang, Feng, et al.
Publicado: (2025)

Effectiveness Assessment of Recent Large Vision-Language Models
por: Jiang, Yao, et al.
Publicado: (2024)

The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
por: Riaz, Hamza, et al.
Publicado: (2025)

Exploring Token Pruning in Vision State Space Models
por: Zhan, Zheng, et al.
Publicado: (2024)

Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
por: Ding, Guanhua, et al.
Publicado: (2024)

FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning
por: Xia, Guoyang, et al.
Publicado: (2025)

Bridge the Modality and Capability Gaps in Vision-Language Model Selection
por: Yi, Chao, et al.
Publicado: (2024)

Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure
por: Yang, Minghao, et al.
Publicado: (2024)