MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba
An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analysis of PEFT methods for Mamba. We investigate the effectiveness of existing PEFT methods for Transformers when applied to Mamba. We also modify these methods to better align with the Mamba architecture. Additionally, we propose new Mamba-specific PEFT methods that leverage the distinctive structure of Mamba. Our experiments indicate that PEFT performs more effectively for Mamba than Transformers. Lastly, we demonstrate how to effectively combine multiple PEFT methods and provide a framework that outperforms previous works. To ensure reproducibility, we will release the code after publication.
Code (1)
Tasks
Mambaparameter-efficient fine-tuningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mamba State-Space Models Are Lyapunov-Stable Learners
Mamba state-space models (SSMs) were recently shown to outperform state-of-the-art (SOTA) Transformer large language models (LLMs) across various tasks. Despite subsequent widespread adaptation, little work has focused o…
In-Context LearningMambaparameter-efficient fine-tuningState Space ModelsCrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression
To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. However, existing methods typically insert…
parameter-efficient fine-tuningImage CompressionParameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
Despite the growing interest in Mamba architecture as a potential replacement for Transformer architecture, parameter-efficient fine-tuning (PEFT) approaches for Mamba remain largely unexplored. In our study, we introduc…
Mambaparameter-efficient fine-tuningState Space ModelsTransfer LearningRoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they …
Common Sense ReasoningMambaPose PredictionRobot Manipulation+2Training-free Token Reduction for Vision Mamba
Vision Mamba has emerged as a strong competitor to Vision Transformers (ViTs) due to its ability to efficiently capture long-range dependencies with linear computational complexity. While token reduction, an effective co…