跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分47

SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models

SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models

AI 導讀

SpaceCast-Bench 評測視覺語言模型的預測性空間推理能力,涵蓋 182 個真實場景、3,862 條問題及 16 種任務。對 21 個模型的評測中,最佳模型得分為 58.0%,低於人類的 87.2%;以程式生成數據微調後,Qwen3-VL-4B 的得分由 34.0% 升至 65.7%。

正文

Published on Oct 8

Authors:

,

,

,

,

,

,

Abstract

Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intelligence demands predictive spatial reasoning: constructing a scene from observations, anticipating how an intervention changes it, and reasoning about the unseen outcome. We introduce SpaceCast-Bench, the first benchmark to directly and diagnostically evaluate this capability. Built around an observe-transform-infer framework, its 3,862 questions from 182 real-world scenes span 16 task types at three levels: static perception, local prediction, and global prediction, progressively requiring scene understanding, spatial state updating, and relational inference over unobserved outcomes. Evaluating 21 models exposes a stark gap: the strongest model reaches only 58.0% against 87.2% human performance, while spatially specialized models remain near random chance. Controlled analyses further reveal that bridge views are critical for integrating distributed observations, and that explicit 3D evidence benefits models more reliably than generated outcome images or videos. Fine-tuning on our programmatically generated data lifts Qwen3-VL-4B from 34.0% to 65.7% with macro-average gains across six out-of-domain benchmarks.

View arXiv page View PDF GitHub Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12402 in a model README.md to link it from this page.

Datasets citing this paper 1

hongxingli/SpaceCast-Bench

Viewer •

Updated 15 minutes ago

•

3.86k

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12402 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