2 papers
cs.CV2026
LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions
Xinnuo Zhang, Zhike Tang, Jing Xu +2
Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. While vision-language models (VL…
cs.HC2026
WidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics
Yutong Chen, Zhike Tang, Zhihao Mai +4
Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level intents into long sequences of in…