CAGE uses LLM-generated code for label-correct diagrams followed by ControlNet-conditioned diffusion refinement to produce both accurate and visually engaging educational graphics, backed by the new EduDiagram-2K dataset.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM-generated declarative specifications bridge natural language what-if questions to interactive interfaces, with benchmarks showing improvement from 52% to 80% success rate after targeted repairs.
citing papers explorer
-
CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement
CAGE uses LLM-generated code for label-correct diagrams followed by ControlNet-conditioned diffusion refinement to produce both accurate and visually engaging educational graphics, backed by the new EduDiagram-2K dataset.
-
Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specification
LLM-generated declarative specifications bridge natural language what-if questions to interactive interfaces, with benchmarks showing improvement from 52% to 80% success rate after targeted repairs.