ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models Paper • 2609.18487 • Published 12 days ago • 47
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation Paper • 2609.06931 • Published 21 days ago • 27
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes Paper • 2609.06652 • Published 22 days ago • 20