[2603.24721] Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.24721 (cs) [Submitted on 25 Mar 2026] Title:Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models Authors:Shengli Zhou, Minghang Zheng, Feng Zheng, Yang Liu View a PDF of the paper titled Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models, by Shengli Zhou and 3 other authors View PDF HTML (experimental) Abstract:Spatial reasoning focuses on locating target objects based on spatial relations in 3D scenes, which plays a crucial role in developing intelligent embodied agents. Due to the limited availability of 3D scene-language paired data, it is challenging to train models with strong reasoning ability from scratch. Previous approaches have attempted to inject 3D scene representations into the input space of Large Language Models (LLMs) and leverage the pretrained comprehension and reasoning abilities for spatial reasoning. However, models encoding absolute positions struggle to extract spatial relations from prematurely fused features, while methods explicitly encoding all spatial relations (which is quadratic in the number of objects) as input tokens suffer from poor scalability. To address these limitations, we propose QuatRoPE, a novel positional embedding method with an input length that is linear to the number of objects, and explicitly calculates pairwise spatial relations through the dot product in attention layers. QuatRo...