Cover Image

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Qizhe, Zou, Bocheng, An, Ruichuan, Liu, Jiaming, Zhang, Shanghang
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
by: Cao, Jiajun, et al.
Published: (2025)

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model
by: Luo, Yulin, et al.
Published: (2024)

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
by: Wang, Haoyu, et al.
Published: (2025)

Agent Skills Should Go Beyond Text: The Case for Visual Skills
by: Xu, Binxiao, et al.
Published: (2026)

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
by: Yang, Senqiao, et al.
Published: (2023)

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
by: Lin, Weifeng, et al.
Published: (2024)

Gradient-based Parameter Selection for Efficient Fine-Tuning
by: Zhang, Zhi, et al.
Published: (2023)

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

Mixture of Physical Priors Adapter for Parameter-Efficient Fine-Tuning
by: Wang, Zhaozhi, et al.
Published: (2024)

SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework
by: Dai, Gaole, et al.
Published: (2025)

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
by: Liu, Jiaming, et al.
Published: (2022)

EVCtrl: Efficient Control Adapter for Visual Generation
by: Yang, Zixiang, et al.
Published: (2025)

MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
by: Zhang, Ronyu, et al.
Published: (2026)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
by: Ma, Junpeng, et al.
Published: (2025)

LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition
by: Zhou, Rixin, et al.
Published: (2025)

Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking
by: Zhu, Yabin, et al.
Published: (2026)

Pear: Pruning and Sharing Adapters in Visual Parameter-Efficient Fine-Tuning
by: Zhong, Yibo, et al.
Published: (2024)

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
by: Cao, Meng, et al.
Published: (2024)

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
by: Zhang, Renrui, et al.
Published: (2024)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language Models
by: Zhao, Shiji, et al.
Published: (2025)

Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition
by: Zhang, Yurong, et al.
Published: (2024)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
by: Zhang, Yuan, et al.
Published: (2024)

A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track
by: Chen, Zehui, et al.
Published: (2024)

Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training
by: Chen, Xinyan, et al.
Published: (2023)

Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective
by: Zhang, Zhi, et al.
Published: (2024)

Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter
by: Zhong, Weizhi, et al.
Published: (2025)

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
by: Zhou, Xin, et al.
Published: (2024)

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
by: Khaki, Samir, et al.
Published: (2025)

SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking
by: Cai, Wenrui, et al.
Published: (2025)

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
by: Wu, Shihan, et al.
Published: (2024)

FreeKD: Knowledge Distillation via Semantic Frequency Prompt
by: Zhang, Yuan, et al.
Published: (2023)

WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal
by: Luo, Yulin, et al.
Published: (2023)

Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
by: Liu, Jiaming, et al.
Published: (2025)

Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision
by: Li, Minglei, et al.
Published: (2024)

Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters
by: Zhou, Yuhang, et al.
Published: (2024)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
by: Liu, Jiaming, et al.
Published: (2024)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
by: Zhang, Qizhe, et al.
Published: (2025)

From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning
by: Jiao, Pengkun, et al.
Published: (2024)