用空间时间监听器解析模型行为，实现可比较的可视化分析。
Visualization of Machine Learning Models through Their Spatial and Temporal Listeners
- 以模型为中心设计双阶段框架，通过抽象监听器捕捉模型时空行为。
- 分析128篇论文331幅图表，发现多数研究聚焦模型结果而非机制。
- 揭示机制类研究影响力高但近年被忽视，适合指导未来可视化设计。
模型可视化（ModelVis）已成为重要研究方向，但现有分类体系多按数据或任务组织，难以将模型本身作为核心分析对象。本文提出一种以模型为中心的两阶段框架，利用抽象监听器捕获模型的空间与时间行为，并将处理后的数据接入经典信息可视化流程。为实现大规模应用，构建了基于检索增强的人类-大语言模型提取工作流，整理出包含128篇VIS/VAST ModelVis论文和331幅编码图示的语料库。分析显示，当前研究普遍优先关注模型输出结果、定量/定性数据类型、统计图表及性能评估；引用加权趋势进一步表明，较少见的模型机制导向研究虽占比低，但影响力显著更高，且近年来关注度持续下降。总体而言，该框架为比较现有模型可视化系统并引导未来设计提供了通用方法。
原文摘要 · Abstract (English)
Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric two-stage framework that employs abstract listeners to capture spatial and temporal model behaviors, and then connects the translated model behavior data to the classical InfoVis pipeline. To apply the framework at scale, we build a retrieval-augmented human--large language model (LLM) extraction workflow and curate a corpus of 128 VIS/VAST ModelVis papers with 331 coded figures. Our analysis shows a dominant result-centric priority on visualizing model outcomes, quantitative/nominal data type, statistical charts, and performance evaluation. Citation-weighted trends further indicate that less frequent model-mechanism-oriented studies have disproportionately high impact while are less investigated recently. Overall, the framework is a general approach for comparing existing ModelVis systems and guiding possible future designs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。