#artificial intelligence
Jun 2026
Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City
It is found that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC), and that Humans answer similarly independent of where they are from (Lima/NYC).
A. Cespedes, Marcelo Chincha, Dunant Cusipuma et al.
· arXiv.org · 0 citations