English
Related papers

Related papers: Training-Free Pretrained Model Merging

200 papers

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Multi-task learning (MTL) concurrently trains a model on diverse task datasets to exploit common features, thereby improving overall performance across the tasks. Recent studies have dedicated efforts to merging multiple independent model…

Machine Learning · Computer Science 2025-06-16 Bingjie Zhang , Hongkang Li , Changlong Shi , Guowei Rong , He Zhao , Dongsheng Wang , Dandan Guo , Meng Wang

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Hongkai Lin , Dingkang Liang , Mingyang Du , Xin Zhou , Xiang Bai

Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility by selectively activating task-relevant parameters and efficiently composing experts across…

Machine Learning · Computer Science 2026-05-20 Guodong Du , Wanyu Lin

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that merging largely preserves or enhances shared knowledge, while…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Timm Hess , Gido M van de Ven , Tinne Tuytelaars

Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze late-stage pre-training trajectories and uncover a…

Machine Learning · Computer Science 2026-05-27 Wenjie Zhou , Bohan Wang , Hongtao Zhang , Chenxi Jia , Wei Chen , Xueqi Cheng

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen has triggered the development of numerous fine-tuned models…

Computation and Language · Computer Science 2025-06-17 Zichuan Fu , Xian Wu , Yejing Wang , Wanyu Wang , Shanshan Ye , Hongzhi Yin , Yi Chang , Yefeng Zheng , Xiangyu Zhao

Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-specific model merging. In this work, we test whether merging can be applied to monolingually…

Computation and Language · Computer Science 2026-05-26 Seth Aycock , Fedor Vitiugin , Aleksandr Umnov , Christof Monz , Khalil Sima'an

Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…

Software Engineering · Computer Science 2026-02-02 You Lu , Jiyang Zhang , Bihuan Chen , Chaofeng Sha , Dingji Wang , Xin Peng

Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives,…

Computation and Language · Computer Science 2026-04-09 Bo Xu , Haotian Wu , Hehai Lin , Weiquan Huang , Beier Zhu , Yao Shu , Chengwei Qin

We present a holistic framework for Continual Model Merging (CMM) that intervenes at three critical stages: pre-merging, during merging, and post-merging-to address two fundamental challenges in continual learning. In particular,…

Machine Learning · Computer Science 2026-02-23 Hoang Phan , Sungmin Cha , Tung Lam Tran , Qi Lei

Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to retraining. Existing methods primarily target resolving conflicts between task updates, leaving the…

Machine Learning · Computer Science 2026-05-22 Yayuan Li , Ze Peng , Jian Zhang , Jintao Guo , Yue Duan , Yinghuan Shi

Large-scale deep learning models with a pretraining-finetuning paradigm have led to a surge of numerous task-specific models fine-tuned from a common pre-trained model. Recently, several research efforts have been made on merging these…

Machine Learning · Computer Science 2025-04-22 Yeoreum Lee , Jinwook Jung , Sungyong Baik

In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective model intelligence through what we call compatible…

Machine Learning · Computer Science 2024-11-05 Jyothish Pari , Samy Jelassi , Pulkit Agrawal

Recent work has shown the promise of creating generalist, transformer-based, models for language, vision, and sequential decision-making problems. To create such models, we generally require centralized training objectives, data, and…

Machine Learning · Computer Science 2023-09-26 Daniel Lawson , Ahmed H. Qureshi

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Xu Liu , Yibo Lu , Xinxian Wang , Xinyu Wu

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques…

Machine Learning · Computer Science 2026-03-03 Chanhyuk Lee , Jiho Choi , Chanryeol Lee , Donggyun Kim , Seunghoon Hong

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Computation and Language · Computer Science 2025-04-01 Neha Verma , Kenton Murray , Kevin Duh

Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the…

Machine Learning · Computer Science 2025-05-23 Chongjie Si , Kangtao Lv , Jingjing Jiang , Yadao Wang , Yongwei Wang , Xiaokang Yang , Wenbo Su , Bo Zheng , Wei Shen
‹ Prev 1 4 5 6 7 8 10 Next ›