Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Paper • 2610.18356 • Published 4 days ago • 120
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 4 days ago • 344
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 3 days ago • 339
Speculative Forcing for Efficient Autoregressive Video Generation Paper • 2610.22347 • Published 1 day ago • 67
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 9 days ago • 70
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments Paper • 2610.10409 • Published 10 days ago • 39
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 10 days ago • 89
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 16 days ago • 91