paper-with-me

Papers

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning

2026-04-21 · Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan arxiv

The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges: (1)Imprecise Routing in the current MoE-LoRA method fails to explicitly match input semantics with expert capabilities, leading to weak expert specialization. (2)Uniform weight fusion strategies struggle to provide adaptive update strengths, overlooking the varying complexity of different tasks. To address these limitations, we propose SAMoRA (Semantic-Aware Mixture of LoRA Experts), a novel parameter-efficient fine-tuning framework tailored for task-adaptive learning. Specifically, A Semantic-Aware Router is proposed to explicitly align textual semantics with the most suitable experts for precise routing. A Task-Adaptive Scaling mechanism is designed to regulate expert contributions based on specific task requirements dynamically. In addition, a novel regularization objective is proposed to jointly promote expert specialization and effective scaling. Extensive experiments on multiple multi-task benchmarks demonstrate that SAMoRA significantly outperforms the state-of-the-art methods and holds excellent task generalization capabilities. Code is available at https://github.com/boyan-code/SAMoRA

📄 PDF Abstract BibTeX arXiv:2604.19048

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningMulti-Task Learning

Similar Papers 제목 키워드 기반

SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images

2025-11-09 · Shuhang Chen, Hangjie Yuan, Pengwei Liu, Hanxue Gu 외 arxiv

The Segment Anything Model (SAM) has demonstrated significant potential in medical image segmentation. Yet, its performance is limited when only a small amount of labeled data is available, while there is abundant valuab…

Medical Image SegmentationSelf-Supervised Learning

Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting

2026-02-13 · Jing Xu, Minglin Wu, Xueyuan Chen, Xixin Wu 외 arxiv

Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose La…

Language IdentificationSpeech Recognition

ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement

2025-08-25 · Raul Balmez, Alexandru Brateanu, Ciprian Orhei, Codruta Ancuti 외 arxiv

We introduce ISALux, a novel transformer-based approach for Low-Light Image Enhancement (LLIE) that seamlessly integrates illumination and semantic priors. Our architecture includes an original self-attention block, Hybr…

Low-Light Image EnhancementSemantic Segmentation

TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models

2026-04-07 · Lin Mu, Haiyang Wang, Li Ni, Lei Sang 외 arxiv

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA expert…

parameter-efficient fine-tuning

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning

2025-06-05 · Ziqi Jia, Anmin Wang, Xiaoyang Qu, Xiaowen Yang 외

Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting the ability to learn high-level planning and multi-level knowledge. To address these…

Continual Learning