跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分35

Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models

Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models

AI 導讀

GPD(Geometry-Privileged Distillation)以幾何線索作為 on-policy self-distillation 的特權,提升視覺語言模型的空間推理能力,部署模型仍只使用 RGB 輸入。

正文

Published on Oct 8

Authors:

,

,

,

,

,

,

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.

View arXiv page View PDF GitHub 3 Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12355 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.12355 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12355 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co