3D-VLA: A 3D Vision-Language-Action Generative World Model
Paper • 2403.09631 • Published • 12
VLA
-
-
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
Paper • 2401.12168 • Published • 30 -
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning
Paper • 2503.03480 • Published -
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
Paper • 2502.20900 • Published • 9