ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models Paper • 2609.18487 • Published 2 days ago • 36
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation Paper • 2609.06931 • Published 11 days ago • 26
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes Paper • 2609.06652 • Published 12 days ago • 22