Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
机构 * Northeastern University(东北大学) ; Microsoft Research(微软研究院) ; University of Southern California(南加州大学) ; University of California, Santa Cruz(加州大学圣克鲁兹分校)
专题命中 视觉空间推理 :reasoning(title,abstract);planning(abstract)
Comments NeurIPS 2025, code link: https://github.com/neu-vi/struct2d