Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions. We introduce Chain-of-Visual-Thought (COVT), a framework that enables VLMs to reason not only in words but also through continuous visual tokens-compact latent representations that encode rich perceptual cues. Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts, capturing complementary properties such as 2D appearance, 3D geometry, spatial layout, and edge structure. During training, the VLM with COVT autoregressively predicts these visual tokens to reconstruct dense supervision signals (e.g., depth, segmentation, edges, and DINO features). At inference, the model reasons directly in the continuous visual token space, preserving efficiency while optionally decoding dense predictions for interpretability. Evaluated across more than ten diverse perception benchmarks, including CV-Bench, MMVP, RealWorldQA, MMStar, WorldMedQA, and HRBench, integrating COVT into strong VLMs such as Qwen2.5-VL and LLaVA consistently improves performance by 3% to 16% and demonstrates that compact continuous visual thinking enables more precise, grounded, and interpretable multimodal intelligence.

翻译：视觉语言模型（VLMs）在语言空间推理方面表现出色，但在需要密集视觉感知的任务（如空间推理和几何认知）中存在局限。这一不足源于当前VLMs缺乏有效机制来捕捉跨空间维度的密集视觉信息。本文提出视觉思维链（COVT）框架，使VLMs不仅能通过语言推理，还能借助连续视觉标记——一种编码丰富感知线索的紧凑潜在表示——进行思考。在约20个标记的有限预算内，COVT从轻量级视觉专家模型中蒸馏知识，捕获包括二维外观、三维几何、空间布局和边缘结构在内的互补属性。训练过程中，配备COVT的VLM通过自回归预测这些视觉标记，以重建密集监督信号（如深度、分割、边缘及DINO特征）。在推理阶段，模型直接在连续视觉标记空间中进行推理，在保持高效的同时，可选择性解码密集预测以提升可解释性。在超过十个多样化感知基准（包括CV-Bench、MMVP、RealWorldQA、MMStar、WorldMedQA和HRBench）上的评估表明，将COVT集成至Qwen2.5-VL和LLaVA等强VLM中，性能持续提升3%至16%，并证明紧凑的连续视觉思维能实现更精确、更可靠且更具可解释性的多模态智能。