arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
By Ningyuan Shi, Zhipeng Zhou, Hao Wang, Chunyan Miao, Peilin Zhao
The paper investigates three fusion paradigms—Merge, Mix RL, and multi‑teacher on‑policy distillation (MOPD)—for consolidating reinforcement learning with verifiable rewards (RLVR) across multiple domains. Experiments across model scales and a multi‑domain benchmark show that while overall performance differences are small, significant gaps can appear on specific tasks, and each method exhibits distinct training dynamics and constraints. Practical guidelines are offered: Merge for cheap fusion when experts exist, Mix RL for unified training with adjustable domain mixtures, and MOPD when preserving domain‑specific gains is paramount.
By Siye Wu, Kai Yang, Yuchen Cai, Xin Xu, Peng-Yuan Wang, Jiaxuan Wang, Jiashun Liu, Jiafei Lyu, Yangkun Chen, Saiyong Yang, Yanghua Xiao
arXiv:2606. 19549v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after both have been fully trained and evaluated.
By Lin Tang, Wei Zhang, Jing Li, Hongyu Chen, Ming Zhao, Yuxuan Wang
arXiv:2610.03199v1 Announce Type: new
Abstract: Large language models fine-tuned from a shared base can be merged by averaging their task vectors, but some merges collapse far below the base model, a...
By Jungseob Lee, Seungyoon Lee, Sugyeong Eo, Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim
ResMerge is a new framework for merging large language models trained via reinforcement learning. It separates each model’s task vector into a leading spectral head and a residual component, finding that both parts contain valuable behavior knowledge but behave differently during merging. The method builds a stable residual backbone using Spherical Residual Consensus Adaptation and then adds a lightweight head correction module that activates only when experts agree, leading to better preservation of expert capabilities compared to existing merging baselines.
By Yandu Sun, Zhiyan Hou, Hongyan An, Weizhen Wang, Haokai Ma, Yuheng Jia, Junfeng Fang, Haiyun Guo, Jinqiao Wang
The paper introduces DiGA, a Disentangled Geometry-Aware framework for merging pretrained models. DiGA orthogonally decomposes each task vector into components tied to distinct geometric attributes, aggregates these components independently, and then recombines them, thereby preserving each component’s geometric identity. Experiments across various models, tasks, and merging methods show that DiGA improves merged-model performance and reduces capability degradation.
By Zijing Wang, Yongkang Liu, Mingyang Wang, Ercong Nie, Mengjie Zhao, Yunpu Ma, Kang Liu, Zihan Wang, Shi Feng, Daling Wang, Hinrich Sch\"utze