[Submitted on 17 Sep 2026 (v1), last revised 10 Oct 2026 (this version, v2)]
Authors:Shuo Cai, Yanggan Gu, Zihao Wang, Yuanyi Wang, Yibo Yan, Wenjun Wang, Yuhang Liu, Guanghao Zhu, Sirui Huang, Ming Li, Hongxia Yang
Abstract:Model fusion integrates the capabilities from source models into a single target model. As of June 2026, Hugging Face hosts more than 2M models. This growing pool provides a rich base for model reuse and capability integration. Yet existing surveys often cover only separate parts of this space, and they do not provide a unified definition or a systematic taxonomy. This survey defines model fusion and organizes prior work into three levels: parameter-level, representation-level, and behavior-level fusion. We also review related metrics, benchmarks, and applications, summarize current challenges, and identify future directions. Our goal is to provide a clear map of this area and support future work on model fusion. A comprehensive list of papers about model fusion is available at this https URL.
Submission history
From: Shuo Cai [view email]
[v1] Thu, 17 Sep 2026 01:24:23 UTC (1,294 KB)
[v2] Sat, 10 Oct 2026 08:55:30 UTC (1,294 KB)
