CoLoGen：面向统一图像生成的概念—定位二元性渐进学习
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
把「语义理解」与「空间定位」两类异质表征显式解耦，再用混合专家式路由（PRW）按阶段融合，为统一条件生成中多任务表征冲突提供了一种可复用的架构思路，可直接迁移到编辑、可控生成与个性化生成的统一模型设计。
原文依据 CoLoGen uses a staged curriculum that first builds core conceptual and localization abilities
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论统一的条件图像生成仍然困难，因为不同任务依赖根本不同的内部表征。有些任务需要概念理解以进行语义合成，另一些则依赖定位线索以获得空间精度。迫使这些异质任务共享单一表征会导致概念—定位的表征冲突。为解决该问题，我们提出 CoLoGen，一个渐进地学习并调和这种概念—定位二元性的统一扩散框架。CoLoGen 采用分阶段课程：首先建立核心的概念与定位能力，然后将其适配到多样的视觉条件，最后精炼二者的协同以应对复杂的指令驱动任务。该过程的核心是渐进表征编织（PRW）模块，它动态地将特征路由到专门的专家，并在各阶段稳定地整合其输出。在编辑、可控生成与定制化生成上的实验表明，CoLoGen 取得了有竞争力或更优的性能，为统一图像生成提供了一个有原则的表征视角。
英文原文摘要 1155 字符
Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for semantic synthesis, while others rely on localization cues for spatial precision. Forcing these heterogeneous tasks to share a single representation leads to concept-localization representational conflict.To address this issue, we propose CoLoGen, a unified diffusion framework that progressively learns and reconciles this concept-localization duality. CoLoGen uses a staged curriculum that first builds core conceptual and localization abilities, then adapts them to diverse visual conditions, and finally refines their synergy for complex instruction-driven tasks. Central to this process is the Progressive Representation Weaving (PRW) module, which dynamically routes features to specialized experts and stably integrates their outputs across stages.Experiments on editing, controllable generation, and customized generation show that CoLoGen achieves competitive or superior performance, offering a principled representational perspective for unified image generation.