English
Related papers

Related papers: DELLA-Merging: Reducing Interference in Model Merg…

200 papers

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention…

Machine Learning · Computer Science 2024-09-30 Chenyu Huang , Peng Ye , Tao Chen , Tong He , Xiangyu Yue , Wanli Ouyang

Averaging the parameters of models that have the same architecture and initialization can provide a means of combining their respective capabilities. In this paper, we take the perspective that this "merging" operation can be seen as…

Machine Learning · Computer Science 2022-08-29 Michael Matena , Colin Raffel

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

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

Existing ML models are known to be highly over-parametrized, and use significantly more resources than required for a given task. Prior work has explored compressing models offline, such as by distilling knowledge from larger models into…

Machine Learning · Computer Science 2022-05-17 Julian Knodt

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Machine Learning · Computer Science 2023-10-30 Prateek Yadav , Derek Tam , Leshem Choshen , Colin Raffel , Mohit Bansal

The proliferation of pre-trained models has given rise to a wide array of specialised, fine-tuned models. Model merging aims to merge the distinct capabilities of these specialised models into a unified model, requiring minimal or even no…

Machine Learning · Computer Science 2025-12-23 Yayuan Li , Jian Zhang , Jintao Guo , Zihan Cheng , Lei Qi , Yinghuan Shi , Yang Gao

Modern deep neural networks (DNNs) consist of millions of parameters, necessitating high-performance computing during training and inference. Pruning is one solution that significantly reduces the space and time complexities of DNNs.…

Machine Learning · Computer Science 2024-04-08 Dhananjay Saikumar , Blesson Varghese

Large language models (LLMs) have achieved significant progress across various domains, but their increasing scale results in high computational and memory costs. Recent studies have revealed that LLMs exhibit sparsity, providing the…

Machine Learning · Computer Science 2025-07-01 Mingkuan Feng , Jinyang Wu , Shuai Zhang , Pengpeng Shao , Ruihan Jin , Zhengqi Wen , Jianhua Tao , Feihu Che

The recent success of specialized Large Language Models (LLMs) in domains such as mathematical reasoning and coding has led to growing interest in methods for merging these expert LLMs into a unified Mixture-of-Experts (MoE) model, with the…

Computation and Language · Computer Science 2025-02-18 Yuhang Zhou , Giannis Karamanolakis , Victor Soto , Anna Rumshisky , Mayank Kulkarni , Furong Huang , Wei Ai , Jianhua Lu

Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios.…

Machine Learning · Computer Science 2025-03-28 Carla Fabiana Chiasserini , Francesco Malandrino , Nuria Molner , Zhiqiang Zhao

Mixture-of-Experts (MoE) enables efficient scaling of large language models by activating only a subset of experts per input token. However, deploying MoE-based models incurs significant memory overhead due to the need to retain all experts…

Machine Learning · Computer Science 2026-02-24 Geng Zhang , Yuxuan Han , Yuxuan Lou , Yiqi Zhang , Wangbo Zhao , Yang You

Magnitude-based pruning is a technique used to optimise deep learning models for edge inference. We have achieved over 75% model size reduction with a higher accuracy than the original multi-output regression model for head-pose estimation.

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Asiri Lindamulage , Nuwan Kodagoda , Shyam Reyal , Pradeepa Samarasinghe , Pratheepan Yogarajah

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Machine Learning · Statistics 2017-11-15 Michael Zhu , Suyog Gupta

Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for…

Machine Learning · Computer Science 2025-10-17 Mohammadsajad Alipour , Mohammad Mohammadi Amiri

Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing…

Computation and Language · Computer Science 2020-10-26 Victor Sanh , Thomas Wolf , Alexander M. Rush

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

Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve adding a few learnable parameters to the fixed backbone model.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Yangyang Guo , Guangzhi Wang , Mohan Kankanhalli

With time, machine learning models have increased in their scope, functionality and size. Consequently, the increased functionality and size of such models requires high-end hardware to both train and provide inference after the fact. This…

Machine Learning · Computer Science 2021-09-07 Arhum Ishtiaq , Sara Mahmood , Maheen Anees , Neha Mumtaz