Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Paper • 2606.19297 • Published • 64
Mikhail Kolosov
idkolosofff
AI & ML interests
RL
Recent Activity
authored a paper 7 months ago
Don't Blind Your VLA: Aligning Visual Representations for OOD
Generalization upvoted a paper 8 months ago
Don't Blind Your VLA: Aligning Visual Representations for OOD
GeneralizationOrganizations
None yet