VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks Paper • 2611.04418 • Published 8 days ago • 27
SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images Paper • 2605.11462 • Published May 12 • 1
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models Paper • 2610.23987 • Published 28 days ago • 39
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Paper • 2608.10299 • Published Aug 10 • 129
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World Paper • 2607.17250 • Published Jul 19 • 87