DuetMerging：协同动态与静态策略以缓解模型合并中的任务干扰
DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Merging
对需要把多个视觉专家模型（如不同域/任务的检测、分割模型）合并成单一多任务网络的研究者，提供了一套可复用的合并流程：先用 Tucker 分解在共享核心张量上构建统一专家池，再用任务特定神经元激活模式生成掩码保留残差关键信息，可直接替换 TIES/DARE 等任务向量合并步骤。
原文依据 we apply Tucker decomposition to a unified tensor of task vectors, creating a harmonized expert pool derived from a shared core tensor
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论模型合并为将多个专家模型整合为单一多任务架构提供了一种有前景的范式。然而，其有效性常受任务干扰的制约，即来自不同任务的冲突参数更新会降低性能。尽管基于混合专家的动态方法提升了适应性，但它们从根本上受限于仅从孤立的各任务向量构建专家池，无法解决任务之间潜在的结构性冲突。本文提出 DuetMerging，一种从动态与静态两个视角协同缓解任务干扰的新框架。在动态方面，我们对任务向量的统一张量施加 Tucker 分解，从共享核心张量构建协调一致的专家池，从而在结构上增强协同并抑制冲突。在静态方面，我们引入基于神经元的稀疏化技术，利用任务特定的神经元激活模式生成精确掩码，从而有选择地保留分解残差中的关键信息，同时抑制功能上无关或冲突的参数。大量实验表明，DuetMerging 优于现有方法，在任务性能与参数效率两方面均达到新的最优。
英文原文摘要 1348 字符
Model merging offers a promising paradigm for consolidating multiple expert models into a single multitask architecture. However, its effectiveness is often hindered by task interference, where conflicting parameter updates from different tasks degrade performance. While dynamic, Mixture-of-Experts based methods have improved adaptability, they are fundamentally limited by constructing their expert pools from task vectors in isolation, failing to resolve underlying structural conflicts across tasks. In this paper, we introduce DuetMerging, a novel framework that synergistically mitigates task interference from both dynamic and static perspectives. Dynamically, we apply Tucker decomposition to a unified tensor of task vectors, creating a harmonized expert pool derived from a shared core tensor that structurally enhances synergies and suppresses conflicts. Statically, we introduce a neuron-based sparsification technique that leverages task-specific neuron activation patterns to create a precise mask. This allows us to selectively preserve critical information from the decomposition's residual while suppressing functionally irrelevant or conflicting parameters. Comprehensive experiments demonstrate that DuetMerging outperforms existing methods, establishing a new state-of-the-art in both task performance and parameter efficiency.