扩散引导的链式视觉：面向大型自回归视觉模型
Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Models
把预训练扩散模型的概率流当作无需任务标注的中间视觉推理步骤，为纯视觉自回归模型提供链式视觉监督；做视觉上下文学习或多步视觉推理时，可复用这一「沿扩散轨迹采样中间图作为推理链」的思路，而不必依赖文本 CoT。
原文依据 pre-trained diffusion models induce a reliable probability flow in image space, where intermediate images sampled along this flow exhibit visual coherence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论思维链（CoT）近期在视觉语言模型中展现出令人鼓舞的进展。然而，纯视觉的思维链（即链式视觉）在视觉上下文学习领域仍未得到充分探索。本文提出扩散引导的链式视觉，借助预训练扩散模型提供的视觉先验，将显式的思维链过程整合进自回归视觉模型。具体而言，我们发现预训练扩散模型在图像空间中诱导出一条可靠的概率流，沿该流采样得到的中间图像具有视觉连贯性，可作为无需任务标注的链式视觉监督，用于纯视觉自回归模型。在多种视觉任务与多尺度模型上的大量实验验证了所提方法在视觉上下文学习中的有效性。代码与数据集将公开。
英文原文摘要 872 字符
Chain-of-Thought (CoT) has recently shown encouraging progress in the vision language model. However, the pure-vision CoT (i.e., chain-of-vision) has been underexplored in visual in-context learning. In this paper, we introduce Diffusion Guided Chain-of-Vision, which integrates an explicit chain-of-thought process into autoregressive vision models through vision prior from pre-trained diffusion models. Concretely, we find that pre-trained diffusion models induce a reliable probability flow in image space, where intermediate images sampled along this flow exhibit visual coherence and serve as task-free, chain-of-vision supervision for pure-vision autoregressive models. Extensive experiments on diverse vision tasks and multi-scale models validate the effectiveness of our proposed method for visual in-context learning. Code and dataset will be publicly available.