{"ID":6029834,"CreatedAt":"2026-07-08T02:57:47.77373338Z","UpdatedAt":"2026-07-10T17:25:22.188537909Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06534","arxiv_id":"2607.06534","title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","abstract":"Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM for multi-room 3D scene understanding. CAIRN aligns transformer attention with scene hierarchy, giving the model explicit awareness of object-level relations and room-level connectivity. It enriches object tokens with room-local relational context via a graph neural network, introduces learned room tokens for room-level abstraction, and applies a hierarchical attention mask with geometric bias to route information according to scene topology. CAIRN is developed on CAIRN-MR, a benchmark we introduce on HM3D for multi-room 3D scene understanding, covering grounding, captioning, and four question-answering tasks that progressively evaluate from intra-room perception to cross-room reasoning. Experiments show that CAIRN outperforms prior 3D-LLMs by a large margin across all CAIRN-MR tasks while remaining competitive on five single-room benchmarks.","short_abstract":"Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM f...","url_abs":"https://arxiv.org/abs/2607.06534","url_pdf":"https://arxiv.org/pdf/2607.06534v1","authors":"[\"He Liang\",\"Chenyang Ma\",\"Yiming Zhang\",\"Sangyun Shin\",\"Andrew Markham\",\"Niki Trigoni\",\"Yuhang He\"]","published":"2026-07-07T17:39:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Graph Neural Network\",\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}