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
SMAT (Simple and Efficient Merge-Aware Training) is a method that jointly optimizes expert loss and expected loss at simulated merged parameters, addressing the shortcomings of standard expert training for model merging. It models common merging operations—Scale, Mask, and Perturb—by sampling scaling coefficients, masks, and additive noise, and introduces efficient techniques such as periodic scheduling, kernel fusion, and parameter storage switching to keep training overhead minimal. Across multiple language and vision-language backbones, SMAT improves mean scores by 1.07–2.16 points over the strongest baseline while adding less than 2% training-time overhead.
By Yanggan Gu, Yuanyi Wang, Zhen Li, Shuo Cai, Yuhang Liu, Junzhuo Li, Zihao Wang, Hongxia Yang
Merge++ is a post‑hoc refinement technique for model merging that synthesizes task‑representative images by inverting expert checkpoints and then distills expert knowledge into a merged model. It operates without any additional data beyond the checkpoints and can be applied universally across existing weight‑space merging algorithms. Experiments show consistent improvements, with average gains of +2 to +8 points and up to +25.9 on specific configurations.
By Aditya Pola, Vineeth N. Balasubramanian
NestedVLA proposes a new approach for consolidating skills in Vision‑Language‑Action models by learning skills independently and then generating task‑specific parameters via a nested hypernetwork, rather than aggregating parameters. The method keeps a frozen base VLA and task‑specific compressed VLM residuals, enabling flexible, interference‑mitigated skill reuse. Experiments on MetaWorld, ManiSkill, and CALVIN show that NestedVLA outperforms the best model‑merging baseline by 41 pp on average and approaches per‑task fine‑tuning performance.
By Guodong Du, Wanyu Lin
arXiv:2606. 19164v1 Announce Type: cross Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model.
By Longhua Li, Lei Qi, Xin Geng, Qi Tian
arXiv:2606. 26902v1 Announce Type: new Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference.
By Jinwook Jung, Taegyu Kim, Kumju Jo, Sungyong Baik
Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic merging models aim to bridge this gap, many works rely on the costly storage and loading of redundant expert components at inference.
arXiv:2609.24517v1 Announce Type: cross
Abstract: Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joi...
By Hyunjoong Cho, Jinhyeok Jang
CORAM introduces a new approach to merging fine‑tuned models by partitioning each target weight matrix into row slices and representing each slice with its singular value decomposition in the base‑model’s SVD frame. The method performs manifold averaging of task‑specific factors and applies an amplification coefficient to counteract contraction, with the coefficient’s scale estimated from update norms and its restoration strength chosen from expert update dispersion. Across multiple model families and scales, CORAM outperforms the prior OrthoMerge technique by up to 1.35 points and matches or exceeds the strongest weight‑space baselines.
CORAM (Coherent Orthogonal Rotation for Model Merging) is a new method for combining fine‑tuned models without joint training or access to original data. It partitions each target weight matrix into row slices, represents each expert slice with its singular value decomposition in the base‑model SVD frame, and merges the task‑specific factors on their corresponding manifolds. The approach includes an amplification coefficient to counteract manifold averaging contraction, spread slicing to balance highly updated rows, and a residual pathway for non‑target layers, achieving improvements over existing orthogonal merging techniques across multiple model families and scales.
By Xinyi Sui, Ziran Liu, Nam Ling, Wei Wang, Wei Jiang
arXiv:2510.14697v2 Announce Type: replace
Abstract: Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent m...
By Bang An, Yibo Yang, Philip Torr, Bernard Ghanem
arXiv:2608. 06699v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments.
By Zibo Shao, Baochen Xiong, Chengdong Xu, Linhui Xiao, Kaichen Li, Haoran Gong, Yan Li, Yaguang Song, Xiaoshan Yang