Methodological Landscape of Heterogeneous LLM Merging
收藏DataCite Commons2026-03-08 更新2026-05-04 收录
下载链接：
https://orkg.org/comparison/R1587759
下载链接
链接失效反馈官方服务：
资源简介：
This table presents heterogeneous LLM merging approaches, where models differ in architecture, training lineage, or parameter structure. It summarizes baseline strategies, architectural assumptions, experimental models and datasets, evaluation metrics, merge space, resource requirements, and additional training dependencies, providing a structured view of cross-architecture integration paradigms.
提供机构：
Open Research Knowledge Graph
创建时间：
2026-03-08
