English
Related papers

Related papers: Subspace-Boosted Model Merging

200 papers

Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging in the context of large (~100B) models, by recycling…

Computation and Language · Computer Science 2025-02-05 Muhammad Khalifa , Yi-Chern Tan , Arash Ahmadian , Tom Hosking , Honglak Lee , Lu Wang , Ahmet Üstün , Tom Sherborne , Matthias Gallé

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT)…

Computation and Language · Computer Science 2025-11-05 Kentaro Ueda , François Portet , Hirohiko Suwa , Keiichi Yasumoto

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Machine Learning · Computer Science 2022-04-27 Raphael Gontijo-Lopes , Yann Dauphin , Ekin D. Cubuk

Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…

Machine Learning · Computer Science 2025-05-23 Zhixu Silvia Tao , Kasper Vinken , Hao-Wei Yeh , Avi Cooper , Xavier Boix

Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive computation. As model merging becomes increasingly prevalent…

Machine Learning · Computer Science 2026-01-01 Enneng Yang , Li Shen , Guibing Guo , Xingwei Wang , Xiaochun Cao , Jie Zhang , Dacheng Tao

Weight-space merging aims to combine multiple fine-tuned LLMs into a single model without retraining, yet most existing approaches remain fundamentally parameter-space heuristics. This creates three practical limitations. First, linear…

Machine Learning · Computer Science 2026-03-06 Jiayu Wang , Zuojun Ye , Wenpeng Yin

Multi-task learning (MTL) is often achieved by merging datasets before fine-tuning, but the growing availability of fine-tuned models has led to new approaches such as model merging via task arithmetic. A major challenge in this setting is…

Machine Learning · Computer Science 2025-09-15 Brahim Touayouch , Loïc Fosse , Géraldine Damnati , Gwénolé Lecorvé

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile…

Machine Learning · Computer Science 2022-06-03 Tianyu Chen , Shaohan Huang , Yuan Xie , Binxing Jiao , Daxin Jiang , Haoyi Zhou , Jianxin Li , Furu Wei

The evolution of biological neural systems has led to both modularity and sparse coding, which enables energy efficiency and robustness across the diversity of tasks in the lifespan. In contrast, standard neural networks rely on dense,…

Machine Learning · Computer Science 2025-02-13 Sagi Shaier , Francisco Pereira , Katharina von der Wense , Lawrence E Hunter , Matt Jones

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

Mixture of expert (MoE) models are a promising approach to increasing model capacity without increasing inference cost, and are core components of many state-of-the-art language models. However, current MoE models typically use only few…

Machine Learning · Computer Science 2025-07-31 Ryo Bertolissi , Jonas Hübotter , Ido Hakimi , Andreas Krause

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

Task Arithmetic is a model merging technique that enables the combination of multiple models' capabilities into a single model through simple arithmetic in the weight space, without the need for additional fine-tuning or access to the…

Machine Learning · Computer Science 2025-07-14 Zhixu Silvia Tao , Ian Mason , Sanjeev Kulkarni , Xavier Boix

Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task…

Machine Learning · Computer Science 2018-06-13 Elliot Meyerson , Risto Miikkulainen

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

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system…

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

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models often experience a loss in their safety…

Artificial Intelligence · Computer Science 2025-06-02 Megh Thakkar , Quentin Fournier , Matthew Riemer , Pin-Yu Chen , Amal Zouaq , Payel Das , Sarath Chandar

The fine-tuning of pre-trained language models has resulted in the widespread availability of task-specific models. Model merging offers an efficient way to create multi-task models by combining these fine-tuned models at the parameter…

Computation and Language · Computer Science 2025-04-29 Sanwoo Lee , Jiahao Liu , Qifan Wang , Jingang Wang , Xunliang Cai , Yunfang Wu

The standard practice for training large language models involves packing multiple documents together to optimize computational efficiency. However, the impact of this process on the models' capabilities remains largely unexplored. To…

Computation and Language · Computer Science 2025-12-17 Gabriele Prato , Shagun Sodhani , Alessandro Sordoni , Sarath Chandar
‹ Prev 1 4 5 6 7 8 10 Next ›