English
Related papers

Related papers: Subspace-Boosted Model Merging

200 papers

Mixtures of Experts combine the outputs of several "expert" networks, each of which specializes in a different part of the input space. This is achieved by training a "gating" network that maps each input to a distribution over the experts.…

Machine Learning · Computer Science 2014-03-11 David Eigen , Marc'Aurelio Ranzato , Ilya Sutskever

Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single…

Machine Learning · Computer Science 2023-09-28 Weishi Li , Yong Peng , Miao Zhang , Liang Ding , Han Hu , Li Shen

Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to representation bias, which can interfere with tasks…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Marcin Osial , Daniel Marczak , Bartosz Zieliński

Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely unexplored. Establishing such theoretical guarantees is non-trivial, as the merging…

Machine Learning · Computer Science 2025-12-25 Seyed Arshan Dalili , Mehrdad Mahdavi

Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks.…

Machine Learning · Computer Science 2023-12-12 Anke Tang , Li Shen , Yong Luo , Liang Ding , Han Hu , Bo Du , Dacheng Tao

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

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

Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integration of diverse LLMs, the overall competency of LLMs is…

Computation and Language · Computer Science 2024-12-23 Mingyang Zhang , Jing Liu , Ganggui Ding , Xinyi Yu , Linlin Ou , Bohan Zhuang

Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding task interference. We argue that its greater potential lies in enabling task synergy, where…

Machine Learning · Computer Science 2026-05-25 Aecheon Jung , Seunghwan Lee , Dongyoon Han , Sungeun Hong

Model merging aims to integrate multiple task-specific models into a unified model that inherits the capabilities of the task-specific models, without additional training. Existing model merging methods often lack consideration of the…

Computation and Language · Computer Science 2025-08-07 Yue Zhou , Yi Chang , Yuan Wu

General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage broad generalization. However, it remains unclear how…

Information Retrieval · Computer Science 2026-02-10 Hengran Zhang , Keping Bi , Jiafeng Guo , Jiaming Zhang , Wenbo Yang , Daiting Shi , Xueqi Cheng

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric…

Information Retrieval · Computer Science 2021-01-22 Luís Borges , Bruno Martins , Jamie Callan

Cross-study replicability is a powerful model evaluation criterion that emphasizes generalizability of predictions. When training cross-study replicable prediction models, it is critical to decide between merging and treating the studies…

Machine Learning · Statistics 2022-07-14 Cathy Shyr , Pragya Sur , Giovanni Parmigiani , Prasad Patil

Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct models with different initializations, each solving a…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 George Stoica , Daniel Bolya , Jakob Bjorner , Pratik Ramesh , Taylor Hearn , Judy Hoffman

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

While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-tuning strategy. Fusing independently trained models with…

Machine Learning · Computer Science 2026-03-05 Sanae Lotfi , Lucas Caccia , Alessandro Sordoni , Jordan T. Ash , Miroslav Dudik

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…

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Ibrahim Almakky , Santosh Sanjeev , Anees Ur Rehman Hashmi , Mohammad Areeb Qazi , Hu Wang , Mohammad Yaqub

Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We…

Machine Learning · Computer Science 2026-03-09 Marmik Chaudhari , Idhant Gulati , Nishkal Hundia , Pranav Karra , Shivam Raval

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