将3D空间推理蒸馏到轻量级视觉-语言模型中：利用推理链
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
AI总结：
本文提出一种知识蒸馏框架，将7B教师模型的3D空间推理能力转移到2.29B学生模型，实现8.7倍更低的推理延迟和3倍模型压缩，同时保留54-72%的性能。引入隐藏推理链提升推理能力，学生模型联合执行空间描述、深度估计和目标检测。
摘要：
大规模3D视觉-语言模型（VLMs）如LLaVA-3D具备强大的空间推理能力，但因计算成本高难以部署。本文提出一种知识蒸馏框架，将7B教师模型的空间推理能力转移到2.29B学生模型。我们的方法实现了8.7倍更低的推理延迟和3倍的模型压缩，同时保留54-72%的教师性能。该框架使用VGGT作为视觉编码器，并采用多任务蒸馏流程结合不确定性感知的损失加权。为提升推理能力而不依赖推理链（CoT）数据，我们引入“隐藏CoT”：可学习的潜在令牌在生成答案前充当内部草稿纸。这是首次在蒸馏的3D VLMs中使用潜在草稿纸推理。学生模型联合执行空间描述、深度估计和目标检测。在ScanNet和3D-FRONT上的实验显示，模型在接近性和接触任务上达到68-72%的准确率。我们的框架使在资源受限平台上高效执行3D场景问答成为可能。
英文摘要：
Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher to a 2.29B student model. Our approach achieves 8.7x lower inference latency and a 3x reduction in model size while retaining 54-72% of the teacher's performance. The framework utilizes VGGT as the vision encoder and a multi-task distillation pipeline with uncertainty-aware loss weighting. To improve reasoning without chain-of-thought (CoT) data, we introduce "Hidden CoT": learnable latent tokens that serve as an internal scratchpad before answer generation. This is the first use of latent scratchpad reasoning in distilled 3D VLMs. The student model jointly performs spatial description, depth estimation, and object detection. Experiments on ScanNet and 3D-FRONT show strong spatial understanding, reaching 68-72% accuracy on proximity and contact tasks. Our framework enables efficient 3D scene QA on resource-constrained platforms.
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。
