---
id: 20261111-T0-18
title: "WorldMind：用潜在世界模拟提升视觉空间推理，应对视角转换任务"
title_en: "WorldMind Uses Latent World Simulation to Boost Visual Spatial Reasoning"
url: https://ai.daily.yangsir.net/daily/20261111-T0-18
issue_date: 2026-11-11
publish_date: 2026-11-10T05:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2611.10151
---

# WorldMind：用潜在世界模拟提升视觉空间推理，应对视角转换任务

arXiv新论文提出WorldMind，针对视觉语言模型在空间推理上的短板，尤其是需要在假设的视角或位置变化下进行心理空间转换的透视取景任务。方法核心是在测试阶段通过潜在世界模拟进行扩展计算，而不是只靠增加模型参数。对多模态研究的实际含义是：测试时扩展这条路线被扩展到空间推理场景，为机器人和具身智能等需要视角推断的任务提供了新思路。

## English Version

**WorldMind Uses Latent World Simulation to Boost Visual Spatial Reasoning**

A new arXiv paper introduces WorldMind, targeting vision-language models' weakness in spatial reasoning, particularly perspective-taking tasks that require mental spatial transformation under hypothetical viewpoint or position changes. The method applies test-time scaling via latent world simulation rather than relying on larger models. For multimodal research, the takeaway is that test-time scaling now extends to spatial reasoning, offering a new angle for robotics and embodied AI tasks that require viewpoint inference.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2611.10151)

**详情页**：https://ai.daily.yangsir.net/daily/20261111-T0-18

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*