掩码至关重要：释放LLM的空间推理能力用于3D场景-语言理解
Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
提出一种无需修改架构和增加参数的注意力掩码策略（3D-SLIM），用几何密度和指令感知替代因果掩码，可直接用于任何基于LLM的3D视觉-语言模型，提升空间推理能力。
原文依据 we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期3D场景-语言理解的进展利用大语言模型（LLM）将通用推理能力迁移到3D多模态上下文中来实现3D推理。然而，现有方法通常采用语言建模中的标准解码器，其依赖于因果注意力掩码。这种设计在3D场景理解中引入了两个根本性冲突：无序3D对象间的顺序偏差以及受限的对象-指令注意力，阻碍了任务特定的推理。为克服这些限制，我们提出了3D空间语言指令掩码（3D-SLIM），这是一种有效的掩码策略，用适应3D场景空间结构的自适应注意力掩码替代因果掩码。我们的3D-SLIM引入两个关键组件：几何自适应掩码，基于空间密度而非词元顺序约束注意力；指令感知掩码，使对象词元能够直接访问指令上下文。该设计允许模型基于空间关系处理对象，同时受用户任务引导。3D-SLIM简单，无需架构修改，不增加额外参数，却在多样化的3D场景-语言任务上带来显著性能提升。跨多个基准和LLM基线的广泛实验验证了其有效性，并强调了解码器设计在3D多模态推理中的关键作用。
英文原文摘要 1464 字符
Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard decoders from language modeling, which rely on a causal attention mask. This design introduces two fundamental conflicts in 3D scene understanding: sequential bias among order-agnostic 3D objects and restricted object-instruction attention, hindering task-specific reasoning. To overcome these limitations, we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes. Our 3D-SLIM introduces two key components: a Geometry-adaptive Mask that constrains attention based on spatial density rather than token order, and an Instruction-aware Mask that enables object tokens to directly access instruction context. This design allows the model to process objects based on their spatial relationships while being guided by the user's task. 3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks. Extensive experiments across multiple benchmarks and LLM baselines validate its effectiveness and underscore the critical role of decoder design in 3D multi-modal reasoning.