Grounded Action Model: 3D Grounding as a Foundation for Robotics Paper • 2609.23863 • Published 22 days ago • 91
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models Paper • 2609.12641 • Published about 1 month ago • 71
RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Paper • 2607.26991 • Published Jul 30 • 10