研究人员开发了两种新方法来增强大型视觉语言模型（LVLM）的空间推理能力。一种方法是软空间推理（Soft Spatial Reasoning），它引入了一个“软思维”框架，允许模型在每个推理步骤中通过混合词嵌入来维持连续的软状态，而不是固定为单个离散词。这种方法包括一个AdaptSoft控制器来管理软化程度，并在各种空间基准测试中表现出改进的性能。第二种方法是Spatial-OPSD，它利用无标签的自蒸馏来提高空间推理能力，而无需依赖真实答案。该框架使用自动获得的空间先验（如深度和3D关系）来训练学生模型，从而实现重复的自我改进，并在多个空间推理基准测试中取得了开源模型中的最先进成果。 AI
影响 这些进展可能带来更强大、更准确的AI系统空间理解能力，这对于具身AI和复杂的视觉任务至关重要。
排序理由 两篇不同的研究论文介绍了改进视觉语言模型空间推理能力的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.38717v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete language tokens. Such hard thinking requires committin…
Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete language tokens. Such hard thinking requires committing to a single token at each step, even when the co…
arXiv:2609.37055v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly operate in embodied and spatially grounded settings, where accurate understanding of depth, viewpoint, and three-dimensional relations is essential. However, improving spatial reasoning typ…