SDO：用于多适配器组合的子空间去冲突算子
SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
浏览论文内容
中文总结 AI 辅助
该研究针对多适配器组合时的身份混淆等问题，提出SDO子空间去冲突算子，通过子空间相关操作优化适配器组合，提升了扩散模型的身份保真度与组合稳定性。
中文摘要 AI 辅助
在共享扩散主干网络中组合独立训练的适配器为多角色生成提供了一种模块化方法，但直接联合部署常导致身份混淆、跨角色属性泄露及场景组合不稳定。我们从参数空间视角研究该干扰，假设其部分源于共享层中重叠主导子空间的冲突。为解决此问题，我们提出SDO（Subspace Deconflicting Operator，子空间去冲突算子）用于多适配器组合。SDO从选定适配器重构分层低秩更新，提取紧凑子空间特征，通过输出子空间重叠度量成对冲突，并应用置换等变变换抑制有害共享方向同时保留身份特定特征。所得表示被映射回标准适配器更新，可直接集成到现有扩散推理管线。实验表明，SDO持续提升身份保真度与组合稳定性，且随着联合组合适配器数量增加，增益尤为显著。
英文摘要
Composing independently trained adapters within a shared diffusion backbone provides a modular approach to multi-character generation, but naive joint deployment often causes identity mixing, cross-character attribute leakage, and unstable scene composition. We study this interference from a parameter-space perspective and hypothesize that it arises partly from conflicts between overlapping dominant subspaces in shared layers. To address this issue, we propose \textbf{SDO}, a \textbf{S}ubspace \textbf{D}econflicting \textbf{O}perator for multi-adapter composition. SDO reconstructs layer-wise low-rank updates from the selected adapters, extracts compact subspace signatures, measures pairwise conflict through output-subspace overlap, and applies a permutation-equivariant transformation that suppresses harmful shared directions while retaining identity-specific characteristics. The resulting representations are mapped back to standard adapter updates and can be directly incorporated into existing diffusion inference pipelines. Experiments demonstrate that SDO consistently improves identity fidelity and compositional stability, with particularly clear gains as the number of jointly composed adapters increases.
发表机构
- University of Auckland（奥克兰大学）
机构由 AI 辅助整理，请以论文原文为准。
