SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 17 days ago • 98
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published 22 days ago • 34
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling Paper • 2610.15166 • Published 26 days ago • 43
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 55
GEBench: Benchmarking Image Generation Models as GUI Environments Paper • 2602.09007 • Published Feb 9 • 39