Abstract
Spatial reasoning in vision language models (VLMs) remains fragile when semantics hinge on subtle temporal or geometric cues. We introduce a synthetic benchmark that probes two complementary skills: situational awareness (recognizing whether an interaction is harmful or benign) and spatial awareness (tracking who does what to whom, and reasoning about relative positions and motion). Through minimal video pairs, we test three challenges: distinguishing violence from benign activity, binding assailant roles across viewpoints, and judging fine-grained trajectory alignment. While we evaluate recent VLMs in a training-free setting, the benchmark is applicable to any video classification model. Results show performance only slightly above chance across tasks. A simple aid, stable color cues, partly reduces assailant role confusions but does not resolve the underlying weakness. By releasing data and code, we aim to provide reproducible diagnostics and seed exploration of lightweight spatial priors to complement large-scale pretraining.
Abstract (translated)
在视觉语言模型（VLMs）中，空间推理依然脆弱，尤其是在语义依赖于微妙的时间或几何线索时。我们引入了一个合成基准测试，该测试考察两种互补技能：情境意识（识别互动是否具有危害性或无害）和空间意识（追踪谁对谁做了什么，并推断相对位置和运动）。通过最小化视频配对，我们测试了三个挑战：区分暴力行为与无害活动、在不同视角下绑定施暴者角色以及判断细微的轨迹对齐。尽管我们在零训练设置中评估了最近的VLMs，但该基准适用于任何视频分类模型。结果表明，在各个任务上的表现仅略高于随机猜测水平。一种简单的辅助手段——稳定颜色线索——部分减少了施暴者角色混淆，但仍未能解决根本弱点。通过发布数据和代码，我们旨在提供可重复诊断工具，并促进对轻量级空间先验的探索，以补充大规模预训练。
URL
https://arxiv.org/abs/2601.15780
