כתבה
arXiv cs.AI ·
Crystalis: יצירת ויזואליזציות רב-מבט
Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation
Crystalis הוא כלי ליצירת ויזואליזציות רב-מבט. הוא משתמש במודלים כמו LLM ו-LangGraph. החידוש מאפשר יצירת ויזואליזציות מורכבות.
תקציר מקורי באנגליתarXiv:2607.24766v1 Announce Type: new Abstract: Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions, remain out of reach. Tight field-level coupling among data transformations, visual encodings, and interaction coordinations causes errors in one component to silently invalidate others. Rather than pursuing end-to-end analytical quality, which depends on model capability, domain knowledge, and user expertise, we target a foundational question: can LLMs reliably produce structurally correct CMVs, and what abstractions make this possible? We present Crystalis, a framework built on query-centric CMV modeling that decomposes a CMV into structured queries over a dependency graph sp
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית