arXiv cs.AI· Hongxing Li, Yixin Li, Dingming Li, Zixuan Wang, Yuchen Yan, Wenqi Zhang, Weiming Lu, Yongliang Shen·· 9 天前AI 评分24
GPD：用路由式 3D 特权蒸馏提升视觉语言模型空间推理能力
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
AI 导读
研究者提出 GPD（Geometry-Privileged Distillation），将深度、语义与鸟瞰图（BEV）线索渲染为紧凑文本，按问题路由给教师模型，仅对错误轨迹施加特权 KL 以增强 GRPO，部署模型仍只用 RGB 输入。
正文 · 原文
Abstract:Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies either inject 3D into the model at inference, paying architecture and latency costs, or train with outcome rewards that supervise only the final answer. Spatial errors originate in perception: a misjudged depth or direction can be corrected only by the scene's true geometry, which the 3D-scanned sources of spatial training corpora already provide. We propose GPD (Geometry-Privileged Distillation), which makes geometric evidence the privilege in on-policy self-distillation (OPSD). For each question, depth, semantic, and bird's-eye-view (BEV) cues are rendered as compact text and routed to the teacher alongside the reference answer; a privileged KL, applied only to incorrect trajectories, augments GRPO, and the deployed model remains RGB-only. On the 4B backbone, GPD achieves 57.1 on VSI-Bench and 37.6 average across MindCube, SPARBench, MMSI-Bench, and ViewSpatial, outperforming both GRPO and answer-privileged OPSD across spatial reasoning benchmarks. Ablations confirm the complementarity of 3D and answer privilege, the advantage of question-conditioned routing over full-context injection, and the benefit of restricting distillation to incorrect trajectories.
| Comments: | Code available at this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12355 [cs.CV] |
| (or arXiv:2610.12355v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12355 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yixin Li [view email]
[v1]
Thu, 8 Oct 2026 17:22:24 UTC (1,855 KB)
来源：arXiv cs.AI · arxiv.org