Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models Paper • 2609.12641 • Published 4 days ago • 61
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models Paper • 2609.12641 • Published 4 days ago • 61
RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Paper • 2607.26991 • Published Jul 30 • 10
RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Paper • 2607.26991 • Published Jul 30 • 10