{"ID":2841688,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11239","arxiv_id":"2511.11239","title":"Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression","abstract":"Existing Vision Language Models (VLMs) architecturally rooted in \"flatland\" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between computationally exorbitant geometric-aware encoders and superficial 2D-only features, and output-stage misalignment where discrete tokenizers are structurally incapable of producing precise, continuous numerical values. To break this impasse, we introduce GEODE (Geometric-Output and Decoupled-Input Engine), a novel architecture that resolves this dual-bottleneck by decoupling 3D reasoning from numerical generation. GEODE augments main VLM with two specialized, plug-and-play modules: Decoupled Rationale Module (DRM) that acts as spatial co-processor, aligning explicit 3D data with 2D visual features via cross-attention and distilling spatial Chain-of-Thought (CoT) logic into injectable Rationale Tokens; and Direct Regression Head (DRH), an \"Embedding-as-Value\" paradigm which routes specialized control tokens to a lightweight MLP for precise, continuous regression of scalars and 3D bounding boxes. The synergy of these modules allows our 1.5B parameter model to function as a high-level semantic dispatcher, achieving state-of-the-art spatial reasoning performance that rivals 7B+ models.","short_abstract":"Existing Vision Language Models (VLMs) architecturally rooted in \"flatland\" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between computationally exorbitant geometric-aware encoders and superficial 2D-only features, a...","url_abs":"https://arxiv.org/abs/2511.11239","url_pdf":"https://arxiv.org/pdf/2511.11239v2","authors":"[\"Zhongbin Guo\",\"Jiahe Liu\",\"Yushan Li\",\"Wenyu Gao\",\"Zhen Yang\",\"Chenzhi Li\",\"Xinyue Zhang\",\"Ping Jian\"]","published":"2025-11-14T12:42:07Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}