most citedBREPS: Bounding-Box Robustness Evaluation of Promptable Segmentation

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Nikita Kachaev, Andrey Moskalenko, Matvey Skripkin +10

Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual kno…