English
Related papers

Related papers: Merging Models on the Fly Without Retraining: A Se…

200 papers

Maintaining robust 3D perception under dynamic and unpredictable test-time conditions remains a critical challenge for autonomous driving systems. Existing test-time adaptation (TTA) methods often fail in high-variance tasks like 3D object…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Huitong Yang , Zhuoxiao Chen , Fengyi Zhang , Zi Huang , Yadan Luo

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Machine Learning · Computer Science 2025-10-17 Ruijie Miao , Yilun Yao , Zihan Wang , Zhiming Wang , Bairen Yi , LingJun Liu , Yikai Zhao , Tong Yang

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 progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Zibo Shao , Baochen Xiong , Xiaoshan Yang , Yaguang Song , Qimeng Zhang , Haifeng Chen , Changsheng Xu

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows,…

Databases · Computer Science 2026-02-17 Yuanyi Wang , Yanggan Gu , Zihao Wang , Kunxi Li , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

Large Language Models (LLMs) face significant challenges in distributed healthcare, including consolidating specialized domain knowledge across institutions while maintaining privacy, reducing computational overhead, and preventing…

Machine Learning · Computer Science 2025-11-18 Prakrit Timilsina , Anuj Nepal , Rajan Kadel , Robin Doss

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Yi-Min Chou , Yi-Ming Chan , Jia-Hong Lee , Chih-Yi Chiu , Chu-Song Chen

When finetuning multiple tasks altogether, it is important to carefully weigh them to get a good performance, but searching for good weights can be difficult and costly. Here, we propose to aid the search with fast previews to quickly get a…

Machine Learning · Computer Science 2024-12-12 Hugo Monzón Maldonado , Thomas Möllenhoff , Nico Daheim , Iryna Gurevych , Mohammad Emtiyaz Khan

Although multi-task learning is widely applied in intelligent services, traditional multi-task modeling methods often require customized designs based on specific task combinations, resulting in a cumbersome modeling process. Inspired by…

Machine Learning · Computer Science 2025-04-15 Jingxuan Zhou , Weidong Bao , Ji Wang , Zhengyi Zhong , Dayu Zhang

Weighted model integration (WMI) extends Weighted model counting (WMC) to the integration of functions over mixed discrete-continuous domains. It has shown tremendous promise for solving inference problems in graphical models and…

Artificial Intelligence · Computer Science 2019-11-21 Zhe Zeng , Guy Van den Broeck

Combining different models is a widely used paradigm in machine learning applications. While the most common approach is to form an ensemble of models and average their individual predictions, this approach is often rendered infeasible by…

Machine Learning · Computer Science 2023-05-17 Sidak Pal Singh , Martin Jaggi

Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional merging approaches combine parameters into a single static…

Computation and Language · Computer Science 2025-05-26 Shuqi Liu , Yuxuan Yao , Bowei He , Zehua Liu , Xiongwei Han , Mingxuan Yuan , Han Wu , Linqi Song

The democratization of machine learning systems has made the process of fine-tuning accessible to practitioners, leading to a wide range of open-source models fine-tuned on specialized tasks and datasets. Recent work has proposed to merge…

Machine Learning · Computer Science 2025-03-03 Anshul Nasery , Jonathan Hayase , Pang Wei Koh , Sewoong Oh

Deep-learning-based nonlinear system identification has shown the ability to produce reliable and highly accurate models in practice. However, these black-box models lack physical interpretability, and a considerable part of the learning…

Machine Learning · Computer Science 2025-07-15 Bendegúz M. Györök , Jan H. Hoekstra , Johan Kon , Tamás Péni , Maarten Schoukens , Roland Tóth

Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more…

Machine Learning · Computer Science 2024-08-27 Anke Tang , Li Shen , Yong Luo , Shuai Xie , Han Hu , Lefei Zhang , Bo Du , Dacheng Tao

Open-vocabulary models like CLIP achieve high accuracy across many image classification tasks. However, there are still settings where their zero-shot performance is far from optimal. We study model patching, where the goal is to improve…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Gabriel Ilharco , Mitchell Wortsman , Samir Yitzhak Gadre , Shuran Song , Hannaneh Hajishirzi , Simon Kornblith , Ali Farhadi , Ludwig Schmidt

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with…

Machine Learning · Computer Science 2021-10-11 Shuo Yang , Le Hou , Xiaodan Song , Qiang Liu , Denny Zhou

Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscape or rely on intractable full-space Hessian approximations.…

Machine Learning · Computer Science 2026-05-27 Juanwu Lu , Anand Bhaskar , Brian Axelrod , Ekaterina Tolstaya , Tristan Emrich

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Yuchuan Mao , Zhi Gao , Xiaomeng Fan , Yuwei Wu , Yunde Jia , Chenchen Jing