Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes Paper • 2609.25247 • Published 4 days ago • 4
H3-World: Turning Language Understanding into World Control Paper • 2609.01560 • Published 24 days ago • 52
H3-World: Turning Language Understanding into World Control Paper • 2609.01560 • Published 24 days ago • 52
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models Paper • 2608.10708 • Published Aug 11 • 16
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle Paper • 2608.04314 • Published Aug 5 • 5
StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation Paper • 2607.26754 • Published Jul 29 • 19
BadWAM: When World-Action Models Dream Right but Act Wrong Paper • 2607.15207 • Published Jul 16 • 45
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models Paper • 2607.06553 • Published Jul 9 • 15
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space Paper • 2607.05373 • Published Jul 6 • 42
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior Paper • 2606.18322 • Published Jun 16 • 16
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior Paper • 2606.18322 • Published Jun 16 • 16