GeoWeaver: 在场景推理前通过几何证据 grounding 视觉 token
GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning
AI总结：
本文提出 GeoWeaver，一种在场景推理前通过几何证据对视觉 token 进行 grounding 的框架，以提升空间推理能力并保持多模态能力。
摘要：
视觉语言模型中的时空推理需要保持物理几何的视觉表示，而非仅仅语义外观。最近的多模态模型通过结构分支、3D感知监督、推理阶段融合或长视界记忆来整合几何信息。尽管这些方法展示了几何对空间智能的重要性，但它们通常将几何线索视为所有视觉 token 的共享信号。我们注意到，这忽略了更细致的挑战：不同的视觉 token 需要根据其空间角色不同的几何证据。为了解决这一限制，我们引入 GeoWeaver，一种预推理的几何 grounding 框架，将几何视为时空推理的表示前提。GeoWeaver 从冻结的几何编码器构建多层次的几何库，并执行 token 自适应的几何证据分配，使每个视觉 token 能够检索最相关的几何抽象。所选证据通过残差 grounding 操作整合到视觉 token 中，在语言建模之前，产生几何 grounding 的表示，以支持后续推理。在空间推理基准上的广泛评估表明，GeoWeaver 一致地增强了几何感知推理，同时保持了通用多模态能力。这表明几何信息带来的最大收益不是作为后期融合的辅助信号，而是作为塑造大型语言模型推理基础的必要前提。所有源代码和模型将在 https://github.com/yahooo-m/GeoWeaver 上发布。
英文摘要：
Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stage fusion, or long-horizon memory. While these approaches demonstrate the importance of geometry for spatial intelligence, they typically treat geometric cues as a shared signal across all visual tokens. We note that this overlooks a finer-grained challenge: different visual tokens require different geometric evidence depending on their spatial roles. To address this limitation, we introduce GeoWeaver, a pre-reasoning geometric grounding framework that treats geometry as a representational prerequisite for spatio-temporal reasoning. GeoWeaver constructs a multi-level geometry bank from a frozen geometry encoder and performs token-adaptive geometric evidence allocation, enabling each visual token to retrieve the most relevant geometric abstractions. The selected evidence is incorporated into visual tokens via a residual grounding operation prior to language modeling, yielding geometry-grounded representations for downstream reasoning. Extensive evaluations on spatial reasoning benchmarks demonstrate that GeoWeaver consistently enhances geometry-aware reasoning while retaining general multimodal capabilities. This indicates that geometric information yields the greatest benefit not as a late-fusion auxiliary signal but as a fundamental prerequisite that shapes the representational foundation on which large language models perform reasoning. All source code and models will be released at https://github.com/yahooo-m/GeoWeaver .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
