English
Related papers

Related papers: Decouple and Orthogonalize: A Data-Free Framework …

200 papers

Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually have heavy inference burden or rely on external knowledge,…

Machine Learning · Computer Science 2026-02-02 Zhan Fa , Yue Duan , Jian Zhang , Lei Qi , Wanqi Yang , Yinghuan Shi

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on…

Machine Learning · Computer Science 2026-05-29 Bethan Evans , Benjamin Etheridge , Stephen Roberts , Jared Tanner

Recent studies have explored the combination of multiple LoRAs to simultaneously generate user-specified subjects and styles. However, most existing approaches fuse LoRA weights using static statistical heuristics that deviate from LoRA's…

Computer Vision and Pattern Recognition · Computer Science 2026-02-18 Qinglong Cao , Yuntian Chen , Chao Ma , Xiaokang Yang

In this study, we evaluate the effect of model merging in ad-hoc retrieval tasks. Model merging is a technique that combines the diverse characteristics of multiple models. We hypothesized that applying model merging to domain-specific…

Information Retrieval · Computer Science 2025-09-29 Taiga Sasaki , Takehiro Yamamoto , Hiroaki Ohshima , Sumio Fujita

Model merging, which combines multiple domain-specialized experts into a single model, offers a practical path to endow Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) with broad capabilities without the cost of…

Machine Learning · Computer Science 2025-10-01 Dengming Zhang , Xiaowen Ma , Zhenliang Ni , Zhenkai Wu , Han Shu , Xin Jiang , Xinghao Chen

Fine-tuning large language models (LLMs) with high parameter efficiency for downstream tasks has become a new paradigm. Low-Rank Adaptation (LoRA) significantly reduces the number of trainable parameters for fine-tuning. Although it has…

Computation and Language · Computer Science 2024-08-14 Jia-Chen Zhang , Yu-Jie Xiong , He-Xi Qiu , Dong-Hai Zhu , Chun-Ming Xia

This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained…

Computation and Language · Computer Science 2025-06-02 Ryota Miyano , Yuki Arase

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that…

Machine Learning · Computer Science 2024-10-22 Ahmed Elbakary , Chaouki Ben Issaid , Tamer ElBatt , Karim Seddik , Mehdi Bennis

Model merging has attracted significant attention as a powerful paradigm for model reuse, facilitating the integration of task-specific models into a singular, versatile framework endowed with multifarious capabilities. Previous studies,…

Machine Learning · Computer Science 2025-01-03 Zhengqi Xu , Han Zheng , Jie Song , Li Sun , Mingli Song

Learning across domains is challenging when data cannot be centralized due to privacy or heterogeneity, which limits the ability to train a single comprehensive model. Model merging provides an appealing alternative by consolidating…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-16 Junming Liu , Yusen Zhang , Rongchao Zhang , Wenkai Zhu , Tian Wu

Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters are typically trained for a single task, limiting their applicability in real-world settings…

Computation and Language · Computer Science 2026-04-21 Seungeon Lee , Soumi Das , Manish Gupta , Krishna P. Gummadi

Fine-tuning large-scale pretrained models is prohibitively expensive in terms of computational and memory costs. LoRA, as one of the most popular Parameter-Efficient Fine-Tuning (PEFT) methods, offers a cost-effective alternative by…

Machine Learning · Computer Science 2024-07-17 Shaowen Wang , Linxi Yu , Jian Li

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Akash Dhasade , Divyansh Jhunjhunwala , Milos Vujasinovic , Gauri Joshi , Anne-Marie Kermarrec

The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a…

Machine Learning · Computer Science 2026-02-16 Haokun Liu , Gyung Hyun Je , Marco Ciccone , Zhenlin Xu , Prasanth YSS , Colin Raffel

Merging or routing low-rank adapters (LoRAs) has emerged as a popular solution for enhancing large language models, particularly when data access is restricted by regulatory or domain-specific constraints. This position paper argues that…

Computation and Language · Computer Science 2025-06-17 Mei-Yen Chen , Thi Thu Uyen Hoang , Michael Hahn , M. Saquib Sarfraz

Parameter-efficient fine-tuning (PEFT) is a flexible and efficient method for adapting large language models (LLMs) to downstream tasks. Among these methods, weight-decomposed low-rank adaptation (DoRA) is a promising approach that…

Machine Learning · Computer Science 2025-08-05 Peijia Qin , Ruiyi Zhang , Pengtao Xie

We systematically investigate the parameter-efficient fine-tuning design space under practical data and compute constraints, and propose D2-LoRA. D2-LoRA achieves 76.4 percent average accuracy across eight question answering and reading…

Machine Learning · Computer Science 2026-02-17 Nozomu Fujisawa , Masaaki Kondo

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…

Machine Learning · Computer Science 2026-04-21 Jin Liu , Yinbin Miao , Ning Xi , Junkang Liu

Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effectively fine-tune LLMs with an extreme reduction in trainable…

Machine Learning · Computer Science 2025-10-23 Reece Shuttleworth , Jacob Andreas , Antonio Torralba , Pratyusha Sharma

Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…

Machine Learning · Computer Science 2024-10-31 Zhan Zhuang , Xiequn Wang , Yulong Zhang , Wei Li , Yu Zhang , Ying Wei