ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models Paper • 2609.18487 • Published 16 days ago • 48
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation Paper • 2605.14712 • Published May 14 • 16
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training Paper • 2605.13757 • Published May 13 • 20