3 papers
cs.LG2026
Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
Wojciech Zarzecki, Jarosław Arabas
Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of…
cs.HC2026
State of the Art of LLM-Enabled Interaction with Visualization
Mathis Brossier, Tobias Isenberg, Konrad Schönborn +5
We report on a systematic, PRISMA-guided survey of research at the intersection of LLMs and visualization, with a particular focus on visio-verbal interaction -- where verbal and v…
cs.HC2026
Piloting Planetarium Visualizations with LLMs during Live Events in Science Centers
Mathis Brossier, Mujtaba Fadhil Jawad, Emma Broman +8
We designed and evaluated an AI pilot in a planetarium visualization software, OpenSpace, for public shows in science centers. The piloting role is usually given to a human working…