paper-with-me

Papers

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models

2025-03-05 · Wonjun Kang, Kevin Galim, Yuchen Zeng, Minjae Lee, Hyung Il Koo, Nam Ik Cho

State Space Models (SSMs) have emerged as efficient alternatives to Transformers, mitigating their quadratic computational cost. However, the application of Parameter-Efficient Fine-Tuning (PEFT) methods to SSMs remains largely unexplored. In particular, prompt-based methods like Prompt Tuning and Prefix-Tuning, which are widely used in Transformers, do not perform well on SSMs. To address this, we propose state-based methods as a superior alternative to prompt-based methods. This new family of methods naturally stems from the architectural characteristics of SSMs. State-based methods adjust state-related features directly instead of depending on external prompts. Furthermore, we introduce a novel state-based PEFT method: State-offset Tuning. At every timestep, our method directly affects the state at the current step, leading to more effective adaptation. Through extensive experiments across diverse datasets, we demonstrate the effectiveness of our method. Code is available at https://github.com/furiosa-ai/ssm-state-tuning.

📄 PDF Abstract BibTeX arXiv:2503.03499

Code (1)

furiosa-ai/ssm-state-tuning 공식 구현 pytorch

Tasks

parameter-efficient fine-tuningState Space Models

Similar Papers 제목 키워드 기반

ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

2025-01-06 · Pengwei Tang, Xiaolin Hu, Yong liu

Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended to the input token embeddings. Recently, …

parameter-efficient fine-tuning

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter

2024-05-29 · Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin 외

Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained visionlang…

Natural Language Queriesparameter-efficient fine-tuningRetrievalTransfer Learning+1

LoFiT: Localized Fine-tuning on LLM Representations

2024-06-03 · Fangcong Yin, Xi Ye, Greg Durrett

Recent work in interpretability shows that large language models (LLMs) can be adapted for new tasks in a learning-free way: it is possible to intervene on LLM representations to elicit desired behaviors for alignment. F…

parameter-efficient fine-tuning

SoTCKGE:Continual Knowledge Graph Embedding Based on Spatial Offset Transformation

2025-03-11 · Xinyan Wang, Jinshuo Liu, Cheng Bi, Kaijian Xie 외

Current Continual Knowledge Graph Embedding (CKGE) methods primarily rely on translation-based embedding methods, leveraging previously acquired knowledge to initialize new facts. To enhance learning efficiency, these me…

Continual LearningGraph EmbeddingKnowledge Graph EmbeddingTranslation

Bayesian Fine-tuning in Projected Subspaces

2026-05-08 · Viktar Dubovik, Patryk Marszałek, Jacek Tabor, Tomasz Kuśmierczyk arxiv

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large models by decomposing weight updates into low-rank matrices, significantly reducing storage and computational overhead. While effective, standar…

parameter-efficient fine-tuningComputational Efficiency