$I^2G$：通过文本条件扩散生成教学插图
$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion
AI总结：
提出语言驱动框架，将程序性文本分解为目标与步骤，通过成分解析、话语连贯模型及新评估协议，在三个数据集上显著优于基线，生成准确反映指令的视觉内容。
摘要：
在自然语言处理（NLP）中，程序性知识的有效沟通仍然是一个重大挑战，因为纯文本指令往往无法传达复杂的物理动作和空间关系。我们通过提出一个语言驱动的框架来解决这一局限性，该框架将程序性文本转化为连贯的视觉指令。我们的方法通过将教学内容分解为目标陈述和顺序步骤来建模其语言结构，然后基于这些语言元素进行视觉生成。我们引入了三项关键创新：（1）基于成分句法分析器的文本编码机制，即使指令较长也能保持语义完整性；（2）成对话语连贯性模型，维持指令序列间的一致性；（3）专门为程序性语言到图像对齐设计的新型评估协议。我们在三个教学数据集（HTStep、CaptainCook4D和WikiAll）上的实验表明，我们的方法在生成准确反映指令语言内容和顺序性质的视觉方面显著优于现有基线。这项工作为程序性语言在视觉内容中落地（grounding）的研究日益增多做出了贡献，其应用涵盖教育、任务指导和多模态语言理解。
英文摘要：
The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey complex physical actions and spatial relationships. We address this limitation by proposing a language-driven framework that translates procedural text into coherent visual instructions. Our approach models the linguistic structure of instructional content by decomposing it into goal statements and sequential steps, then conditioning visual generation on these linguistic elements. We introduce three key innovations: (1) a constituency parser-based text encoding mechanism that preserves semantic completeness even with lengthy instructions, (2) a pairwise discourse coherence model that maintains consistency across instruction sequences, and (3) a novel evaluation protocol specifically designed for procedural language-to-image alignment. Our experiments across three instructional datasets (HTStep, CaptainCook4D, and WikiAll) demonstrate that our method significantly outperforms existing baselines in generating visuals that accurately reflect the linguistic content and sequential nature of instructions. This work contributes to the growing body of research on grounding procedural language in visual content, with applications spanning education, task guidance, and multimodal language understanding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
