• GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs Junqing Du, Fernando Ropero, Erkin Turkoz, et al. · arXiv:2609.03892
• Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning Yijun Yang, Shenghe Zheng, Wenbo Li, et al. · arXiv:2609.03729