做具身智能或3D视觉问答的团队，终于有了一个不用暴力融合所有模态的轻量方案——MASER根据问题语义动态选最优模态，点云在超半数场景下最准，值得在Open3D-VQA上试试。
MASER 提出了一种轻量级框架，解决现有视觉语言模型（VLM）在3D环境中仅针对单一模态微调、忽略问题语义可能更适合其他模态的问题。该框架在共享VLM骨干上训练五个不同模态适配器（自然语言、RGB图像、点云、深度图、相机姿态），并通过神经路由策略在推理时根据问题选择最优适配器。在Open3D-VQA基准测试中，点云模态在51.5%情况下最优，MASER的路由准确率达到51.3%的oracle一致性，优于随机森林的43.5%，且每次推理仅需一次适配器调用。这项工作为具身智能体在3D空间中的多模态推理提供了高效解决方案。
MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence
In 3D environments, Embodied Agents answer spatially relevant questions through reasoning from a mixture of modalities including natural language, RGB images, point clouds, depth maps and camera poses. Existing Vision-Language models (VLMs) are fine-tuned over a single modality. This completely ignores the question semantics which may favor a different modality than the finetuned modality. To address this, we propose MASER (Modality-Adaptive SpEcialist Routing), a lightweight framework that trains five different modality adapters of a shared VLM backbone and learns a neural routing policy that selects the best adapter based on the question during inference. We encode each question with a frozen sentence transformer and pass the embedding through a small Multi-layer Perceptron (MLP) trained on oracle adapter-accuracy labels. We evaluate our methodology over the Open3D-VQA benchmark and our evaluations show that no single modality is universally optimal -- point-cloud answers are best in 51.5% of cases. MASER routes with 51.3% oracle agreement, outperforming a Random-Forest ablation (43.5%), with only a single adapter call per question.