The paper introduces a data‑free method for model merging that estimates per‑layer covariance matrices directly from difference matrices, eliminating the need for auxiliary data. This approach reduces computational costs while maintaining a principled interference‑minimization framework. Experiments on vision and language benchmarks with models from 86 M to 7 B parameters show that the method outperforms existing data‑free merging techniques.
By Marawan Gamal Abdel Hameed, Derek Tam, Pascal Jr Tikeng Notsawo, Colin Raffel, Guillaume Rabusseau
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.
CAMFT is a Conflict‑Aware Mergeable Fine‑Tuning method designed to make task adaptation efficient and merge‑aware for large language models. Unlike existing approaches that only resolve parameter conflicts after fine‑tuning, CAMFT shapes mergeability during training by guiding each task to update sparse coordinates with lower cross‑task conflict. Experiments show that CAMFT outperforms standard fine‑tuning baselines in multi‑task merging scenarios.
By Jingang Zhou, Haiyang Guo, Yuan Ma, Han Zhu, Xu-Yao Zhang
arXiv:2610.07990v1 Announce Type: new
Abstract: Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models. To perform well across multiple tas...
By Sin-Han Yang, Shih-Cheng Huang, Chieh-Yen Lin, Yun-Nung Chen, Shao-Hua Sun, Hung-yi Lee
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. 22589v2 Announce Type: replace Abstract: Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-task model.
By Jungyong Son, Jinwook Jung, Sungyong Baik
arXiv:2606.19164v4 Announce Type: replace-cross
Abstract: Model merging enables training-free multi-task learning by aggregating knowledge from models fine-tuned from a shared checkpoint, but their t...
By Longhua Li, Lei Qi, Qi Tian, Xin Geng
The paper introduces a new multi‑task model‑merging framework that tackles task interference by projecting task vectors into a high‑dimensional sparse feature space using Sparse Autoencoders, enabling feature‑level disentanglement before fusion. It also proposes a lightweight Group‑Ranked Zeroth‑Order Optimizer to identify task‑critical layers for selective merging, reducing computational overhead. Experiments on Qwen2.5‑1.5B and Qwen2.5‑7B show consistent performance gains over several baselines across reasoning, code generation, instruction following, and general knowledge tasks, with a 2.78% improvement in a highly conflicting four‑task setting.
By Yihang Zhang, Shengke Sun, Junjie Wen, Feng Zeng
arXiv:2607. 01689v1 Announce Type: cross Abstract: Model merging aims to combine existing single-task solutions into a multi-task solution without additional data-driven fine-tuning.
By Long Minh Bui, Tuan Anh Le Van, Tung Phi Duc, Phi Le Nguyen, Jana Doppa, Trong Nghia Hoang
Model merging provides an efficient way to construct multi-task generalist models without additional training, but its performance often degrades under severe task interference. Task interference in m...
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