{"ID":6138580,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-10T09:20:07.340435153Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06620","arxiv_id":"2607.06620","title":"SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts","abstract":"Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry. Existing 3D-aware models either rely on costly 3D-specific data or utilize RGB-only inputs with heuristic sampling and monolithic, shallow fusion, which respectively disrupt essential spatiotemporal connectivity and induce modality contention across diverse spatial tasks. To overcome these bottlenecks, we introduce SpaR3D-MoE, an end-to-end framework that enables adaptive spatial reasoning by equipping MLLMs with geometry-aware capabilities from only sparse RGB inputs. First, we propose an adaptive spatiotemporal manifold sampling mechanism that constructs a geometry-aware spatiotemporal graph to extract informative keyframes, effectively mitigating sequence redundancy while preserving the scene's topological connectivity. Second, we introduce the heterogeneous geometry-inductive Mixture-of-Experts driven by an instruction-pose aware router, which adaptively routes multimodal tokens to specialized experts, resolving the cross-modal contention inherent in monolithic fusion. Extensive experiments on VSI-Bench, ScanQA, and SQA3D demonstrate that our method achieves state-of-the-art performance. Notably, SpaR3D-MoE achieves the highest average score of 63.5 on VSI-Bench, outperforming the strongest baseline by 7.8 absolute points, alongside relative improvements of 35.4% and 51.4% in Route Plan and Relative Direction tasks, respectively.","short_abstract":"Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry. Existing 3D-aware models either rely on costly 3D-specific data or utilize RGB-only inputs with heuristic sampling and monolithic, shallow fusion, which respectively dis...","url_abs":"https://arxiv.org/abs/2607.06620","url_pdf":"https://arxiv.org/pdf/2607.06620v1","authors":"[\"Haida Feng\",\"Hao Wei\",\"Haolin Wang\",\"Shiwei Li\",\"Chade Li\",\"Yihong Wu\"]","published":"2026-07-07T09:27:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}