Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Paper • 2601.16211 • Published 14 days ago • 50
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space Paper • 2607.05373 • Published 10 days ago • 64
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Paper • 2606.29513 • Published 18 days ago • 52
Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams Paper • 2606.15200 • Published Jun 13 • 1
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper • 2605.07755 • Published May 8 • 24