Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Paper • 2606.19297 • Published • 81
Sergey Kolyubin
SKRobotics
AI & ML interests
Embodied intelligence, resilient autonomy, adaptive systems
Organizations
upvoted a paper 3 months ago
upvoted 5
papers 5 months ago
OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions
Paper • 2503.10331 • Published • 5
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Paper • 2604.24764 • Published • 121
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
Paper • 2602.00919 • Published • 322
KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM
Paper • 2512.01889 • Published • 3
RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments
Paper • 2604.26067 • Published • 77