English
Related papers

Related papers: Mixup Model Merge: Enhancing Model Merging Perform…

200 papers

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Zhijun Mai , Guosheng Hu , Dexiong Chen , Fumin Shen , Heng Tao Shen

Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For example, in Task Arithmetic (TA), adding the fine-tuned weights…

Machine Learning · Computer Science 2025-01-10 Feng Xiong , Runxi Cheng , Wang Chen , Zhanqiu Zhang , Yiwen Guo , Chun Yuan , Ruifeng Xu

The generalization ability of most meta-reinforcement learning (meta-RL) methods is largely limited to test tasks that are sampled from the same distribution used to sample training tasks. To overcome the limitation, we propose Latent…

Machine Learning · Computer Science 2022-01-19 Suyoung Lee , Sae-Young Chung

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…

Machine Learning · Computer Science 2026-01-21 Xiangchi Yuan , Dachuan Shi , Chunhui Zhang , Zheyuan Liu , Shenglong Yao , Soroush Vosoughi , Wenke Lee

In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple…

Computation and Language · Computer Science 2024-11-26 Bingdong Li , Zixiang Di , Yanting Yang , Hong Qian , Peng Yang , Hao Hao , Ke Tang , Aimin Zhou

Multi-task learning (MTL) compresses the information from multiple tasks into a unified backbone to improve computational efficiency and generalization. Recent work directly merges multiple independently trained models to perform MTL…

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

Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models without requiring access to raw training data. However, in this paper, we examine the merged model's…

Machine Learning · Computer Science 2024-10-21 Enneng Yang , Li Shen , Zhenyi Wang , Guibing Guo , Xingwei Wang , Xiaocun Cao , Jie Zhang , Dacheng Tao

As specialized large language models (LLMs) become increasingly prevalent, model merging methods are being used to combine them to create a single multi-task model without requiring any additional data or training. However, these approaches…

Machine Learning · Computer Science 2025-03-11 Hetarth Chopra , Vidhi Rambhia , Vikram Adve

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…

Computation and Language · Computer Science 2025-05-23 Xisen Jin , Xiang Ren , Daniel Preotiuc-Pietro , Pengxiang Cheng

Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency…

Machine Learning · Computer Science 2026-03-17 Han-Chen Zhang , Zi-Hao Zhou , Mao-Lin Luo , Shimin Di , Min-Ling Zhang , Tong Wei

With the rapid development of 3D printing, the demand for personalized and customized production on the manufacturing line is steadily increasing. Efficient merging of printing workpieces can significantly enhance the processing efficiency…

Artificial Intelligence · Computer Science 2025-04-04 Yuhao Liu , Maolin Yang , Pingyu Jiang

Large language models (LLMs) have become increasingly capable, but their development often requires substantial computational resources. While model merging has emerged as a cost-effective promising approach for creating new models by…

Neural and Evolutionary Computing · Computer Science 2025-01-28 Takuya Akiba , Makoto Shing , Yujin Tang , Qi Sun , David Ha

Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons,…

Machine Learning · Computer Science 2020-03-17 Yueh-Hua Wu , Ting-Han Fan , Peter J. Ramadge , Hao Su

Large language models (LLMs) have enabled the development of numerous specialized, task-specific variants. However, the maintenance and deployment of these individual models present substantial challenges in terms of resource utilization…

Machine Learning · Computer Science 2024-11-04 Quy-Anh Dang , Chris Ngo

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

Model merging has emerged as a promising technique for combining multiple fine-tuned models into a single multitask model without retraining. However, the factors that determine whether merging will succeed or fail remain poorly understood.…

Computation and Language · Computer Science 2026-01-13 Adir Rahamim , Asaf Yehudai , Boaz Carmeli , Leshem Choshen , Yosi Mass , Yonatan Belinkov

A data mixture refers to how different data sources are combined to train large language models, and selecting an effective mixture is crucial for optimal downstream performance. Existing methods either conduct costly searches directly on…

Machine Learning · Computer Science 2026-05-07 Jingwei Li , Xinran Gu , Jingzhao Zhang

MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data…

Machine Learning · Computer Science 2018-11-26 Hongyu Guo , Yongyi Mao , Richong Zhang

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

Recent advancements in reinforcement learning (RL) for analog circuit optimization have demonstrated significant potential for improving sample efficiency and generalization across diverse circuit topologies and target specifications.…

Machine Learning · Computer Science 2024-11-26 Youngmin Oh , Jinje Park , Seunggeun Kim , Taejin Paik , David Pan , Bosun Hwang