Figureure 2 · Overview of COREFigure 2. Overview of CORE. Our framework consists of two key pathways. The primary data flow, indicated by solid lines, shows how compact object-centric representations are generated and processed by the language decoder. This process is informed by the auxiliary segmentation head, shown with dashed lines, which produces the object masks that guide the token merging. The icon in the top-left corner of each mask denotes a different object in the image.这张图概括 CORE 的整体方法流程。阅读时先看模块之间传递的训练信号,再看作者如何把目标拆成可优化的子问题。Figure S5Figure S5. Comparison on Objects’ Positional Relationship Detection. Incorrect and correct model responses are highlighted in red and green, respectively.这张图/表用于判断 CORE 的实验收益来自哪里。重点看替换、消融或跨模型设置下趋势是否一致,而不是只看单个最高分。