English
Related papers

Related papers: Mitigating Parameter Interference in Model Merging…

200 papers

Model merging is an effective post-training strategy for composing capabilities in large language models without joint retraining. We study this in the supervised fine-tuning (SFT) stage, where multiple capability-based SFT checkpoints --…

Machine Learning · Computer Science 2025-09-16 Pouria Mahdavinia , Hamed Mahdavi , Niloofar Mireshghallah , Mehrdad Mahdavi

Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector has become a fundamental building block, as it can…

Artificial Intelligence · Computer Science 2025-10-17 Bang An , Yibo Yang , Philip Torr , Bernard Ghanem

Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, models trained independently on distinct tasks often exhibit…

Machine Learning · Computer Science 2026-03-17 Pratik Ramesh , George Stoica , Arun Iyer , Leshem Choshen , Judy Hoffman

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensembles, work well, but are expensive in terms of memory and…

Machine Learning · Computer Science 2024-12-23 Albert Manuel Orozco Camacho , Stefan Horoi , Guy Wolf , Eugene Belilovsky

Parameter-efficient fine-tuning (PEFT) of pre-trained language models has recently demonstrated remarkable achievements, effectively matching the performance of full fine-tuning while utilizing significantly fewer trainable parameters, and…

Computation and Language · Computer Science 2023-05-29 Baohao Liao , Yan Meng , Christof Monz

Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…

Computation and Language · Computer Science 2025-05-30 Haobo Zhang , Jiayu Zhou

With the development of large language models, fine-tuning has emerged as an effective method to enhance performance in specific scenarios by injecting domain-specific knowledge. In this context, model merging techniques provide a solution…

Computation and Language · Computer Science 2025-09-18 Zijian Li , Xiaocheng Feng , Huixin Liu , Yichong Huang , Ting Liu , Bing Qin

Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not been actively used in real-world applications due to its…

Machine Learning · Computer Science 2025-03-17 Junhyuk Jo , Jihyun Lim , Sunwoo Lee

Multi-task learning (MTL) aims to empower a model to tackle multiple tasks simultaneously. A recent development known as task arithmetic has revealed that several models, each fine-tuned for distinct tasks, can be directly merged into a…

Machine Learning · Computer Science 2024-05-29 Enneng Yang , Zhenyi Wang , Li Shen , Shiwei Liu , Guibing Guo , Xingwei Wang , Dacheng Tao

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Artificial Intelligence · Computer Science 2025-03-28 Jiaqi Han , Jingwen Ye , Shunyu Liu , Haofei Zhang , Jie Song , Zunlei Feng , Mingli Song

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalization parameters…

Machine Learning · Computer Science 2023-11-20 Maximilian Mueller , Tiffany Vlaar , David Rolnick , Matthias Hein

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Computation and Language · Computer Science 2026-03-31 Mingyang Song , Mao Zheng

Large language models, such as ChatGPT, Claude, or LLaMA, are gigantic, monolithic, and possess the superpower to simultaneously support thousands of tasks. However, high-throughput applications often prefer smaller task-specific models…

Computation and Language · Computer Science 2025-02-17 Haoyu Yang , Zheng Zhang , Saket Sathe

The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In…

Computation and Language · Computer Science 2024-09-06 Wei Lu , Rachel K. Luu , Markus J. Buehler

Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Shengzhuang Chen , Jihoon Tack , Yunqiao Yang , Yee Whye Teh , Jonathan Richard Schwarz , Ying Wei

Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often induce the "seesaw effect": optimizing for one task may…

Computation and Language · Computer Science 2026-01-27 Xiaoyu Liu , Xiaoyu Guan , Di Liang , Xianjie Wu

While most current approaches rely on further training techniques, such as fine-tuning or reinforcement learning, to enhance model capacities, model merging stands out for its ability of improving models without requiring any additional…

Computation and Language · Computer Science 2025-05-26 Zehua Liu , Han Wu , Yuxuan Yao , Ruifeng She , Xiongwei Han , Tao Zhong , Mingxuan Yuan

Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model…

Machine Learning · Computer Science 2026-03-10 Levy Chaves , Chao Zhou , Rebekka Burkholz , Eduardo Valle , Sandra Avila

Foundation models have revolutionized artificial intelligence by providing robust, versatile architectures pre-trained on large-scale datasets. However, adapting these massive models to specific downstream tasks requires fine-tuning, which…

Machine Learning · Computer Science 2025-05-01 Jieming Bian , Yuanzhe Peng , Lei Wang , Yin Huang , Jie Xu

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…