The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study

ArXi:2504.04540v2 Announce Type: replace-cross 3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some promising results, the advantages of point clouds over other modalities remain unclear. Moreover, existing 3D benchmarks are insufficient for fairly evaluating the ability of multimodal LLMs to comprehend spatial concepts. To address these challenges, we